(Click on AD Number to retrieve full text PDF version of document)
Performance and Usage of Biometrics in a Testbed Environment for Tactical Purposes
Personal Author(s): Verett, Marianna J
Report Date: Dec 2006
Descriptors: (U) *TEST BEDS, *IDENTIFICATION SYSTEMS, *BIOMETRY, *NETWORK TOPOLOGY, DATA TRANSMISSION SYSTEMS, SATELLITE COMMUNICATIONS, SPECIAL OPERATIONS FORCES, FINGERPRINT RECOGNITION, TACTICAL ANALYSIS, SPECIFICATIONS, THESES
Identifiers: (U) *ABIS(AUTOMATED BIOMETRIC IDENTIFICATION SYSTEMS), ELECTRONIC BIOMETRIC TRANSMISSION SPECIFICATION, ELECTRONIC FINGERPRINT TRANSMISSION SPECIFICATION, CROSS MATCH, TNP(TACTICAL NETWORK TOPOLOGY), IRIDIUM SATELLITE, UV(UNMANNED VEHICLES)
Abstract: (U) Naval Postgraduate School's (NPS) Tactical Network Topology (TNT) experiments seek to develop, implement and identify sensor-unmanned vehicle network, and network centric operations to assist DoD warfighters in the Global War on Terrorism (GWOT). Using biometric data for rapid identification of High Value Targets (HVT) in ground and Maritime Interdiction Operations (MIO) is critical to the emerging special operation concept. The goal is to explore solutions and operational constraints associated with biometrics data analysis and rapid identification by means of ad hoc self forming sensor unmanned vehicle (UV) wireless networks. The objectives of this thesis are to look at how biometrics has performed in a testbed environment that is simulating a real special operations environment in theatre. This thesis is meant to explore and explain the biometrics process that was conducted on top of the tactical network and evaluate its performance. This thesis provided the process model for biometrics identification in the tactical networks environment. This thesis also evaluated the length of time that it took to transmit the fingerprint data from the field to the ABIS database, with an identification result then sent back to the field. The longest time that was observed was 70 minutes (using low bandwidth Satellite communications), while the shortest time was 4 minutes for reachback to ABIS and 2 minutes for a local database.
Radicalization: Homeland Security Implication
Personal Author(s): Woodward, Jr , John D
Report Date: 20 Sep 2006
Descriptors: (U) *IDENTIFICATION, *BIOMETRY, *HOMELAND SECURITY, DATA BASES, NATIONAL SECURITY, INFORMATION EXCHANGE
Identifiers: (U) IDENTITY MANAGEMENT, BIOMETRICS, ISE(INFORMATION SHARING ENVIRONMENT)
Abstract: (U) Today, I want to make two basic points with respect to biometrics, which are automated methods of recognizing a person based on a physiological or behavioral characteristic: 1. The U.S. Government is currently using biometric technologies in various ways to make the nation safer. 2. We can and should make better use of these technologies for homeland security purposes.
Back to Top
Statistical Approach to Background Subtraction for Production of High-Quality Silhouettes for Human Gait
Personal Author(s): Samler, Jennifer J
Report Date: Sep 2006
Descriptors: (U) *IMAGE PROCESSING, *HUMANS, *SILHOUETTES, *IDENTIFICATION, MOTION, THESES, BACKGROUND, BIOMETRY
Identifiers: (U) *GAIT RECOGNITION, *BACKGROUND SUBTRACTION, HUMAN GAIT, VIDEO DATA, BIOMETRICS
Abstract: (U) This thesis uses a background subtraction to produce high-quality silhouettes for use in human identification by human gait recognition, an identification method which does not require contact with an individual and which can be done from a distance. A statistical method which reduces the noise level is employed resulting in cleaner silhouettes which facilitate identification. The thesis starts with gathering video data of individuals walking normally across a background scene. From there the video is converted into a sequence of images that are stored as joint photographic experts group (jpeg) files. The background is subtracted from each image using a developed automatic computer code. In those codes, pixels in all the background frames are compared and averaged to produce an average background picture. The average background picture is then subtracted from pictures with a moving individual. If differenced pixels are determined to lie within a specified region, the pixel is colored black, otherwise it is colored white. The outline of the human figure is produced as a black and white silhouette. This inverse silhouette is then put into motion by recombining the individual frames into a video.
Defense in Depth: Foundation for Secure and Resilient IT Enterprises
Personal Author(s): May, Christopher J, Hammerstein, Josh, Mattson, Jeff, Rush, Kristopher
Report Date: Sep 2006
Media Count: 365 Page(s)
Descriptors: (U) *SOFTWARE ENGINEERING, *INFORMATION SYSTEMS, *DATA PROCESSING SECURITY, *COURSES(EDUCATION), *MANAGEMENT TRAINING, *INFORMATION ASSURANCE, *DEFENSE IN DEPTH, POLICIES, STANDARDS, REGULATIONS, CONFIGURATION MANAGEMENT, BIOMETRIC SECURITY, INFORMATION SECURITY, RISK MANAGEMENT, RISK ANALYSIS, LIFE CYCLE MANAGEMENT, ACCOUNTABILITY, SECURITY PERSONNEL, ADMINISTRATIVE PERSONNEL, MANAGEMENT PERSONNEL, AVAILABILITY, CRYPTOGRAPHY, CRISIS MANAGEMENT
Identifiers: (U) DEFENSE-IN-DEPTH, COMPLIANCE MANAGEMENT, IDENTITY MANAGEMENT, AUTHORIZATION MANAGEMENT, ACCOUNTABILITY MANAGEMENT, AVAILABILITY MANAGEMENT, CONFIGURATION MANAGEMENT, INCIDENT MANAGEMENT, INFORMATION TECHNOLOGY, INSTRUCTIONAL MODULES
Abstract: (U) The Defense-in-Depth Foundational Curriculum is designed for students ranging from system administrators to CIOs who have some technical understanding of information systems and want to delve into how technical assurance issues affect their entire organizations. The course material takes a big-picture view while also reinforcing concepts presented with some details about implementation. Therefore, this course can be a useful pursuit for system administrators and IT security personnel who would like to step up to the management level. It also can provide a refresher for IT managers and executives who want to stay up to date on the latest technological threats facing their enterprises. The curriculum consists of eight main modules: (1) Compliance Management, (2) Risk Management, (3) Identity Management, (4) Authorization Management, (5) Accountability Management, (6) Availability Management, (7) Configuration Management, and (8) Incident Management. The document also contains an introduction, "Foundations of Information Assurance," which focuses on how the overarching concepts of confidentiality, integrity, and availability can lead to a comprehensive security strategy.
Uncooled Infrared Imaging Face Recognition Using Kernel-Based Feature Vector Selection Personal Author(s): Alexandropoulos, Ioannis M
Report Date: Sep 2006
Descriptors: (U) *INFRARED IMAGES, *PATTERN RECOGNITION, *FACE(ANATOMY), DATA BASES, VERIFICATION, LOW RESOLUTION, CLASSIFICATION, STATISTICAL TESTS, THESES
Identifiers: (U) *FACE RECOGNITION
Abstract: (U) A considerable amount of research has been recently conducted on face recognition tasks, due to increasing demands for security and authentication applications. Recent technological developments in uncooled IR imagery technology have boosted IR face recognition research applications. Our study is part of an on-going research initiated at the Naval Postgraduate School that considers an uncooled low-resolution and low-cost IR camera used for face recognition applications. This work investigates a recent approach which approximates nonlinear kernel-based methods at a significantly reduced computational cost. Our research was applied to an IR database. Results show that this scheme may perform sufficiently close to its "kernelized" version considered in a previous study, at a fraction of the computational cost, provided that the associated parameters are well tuned. The thesis considers a relative comparison between the two algorithms, based on identification and verification experiments and considers a statistical test to investigate whether classification performance differences may be considered statistically significant. Results show that, from a cost perspective, a low-resolution uncooled IR camera in conjunction with a low computational-cost classification scheme can be embedded in a robust face recognition system to efficiently address the issue of authentication in security-related tasks.
The National Biometrics Challenge
Report Date: Aug 2006
Descriptors: (U) *POLICIES, *BIOMETRIC SECURITY, UNITED STATES GOVERNMENT, INFORMATION EXCHANGE, REAL TIME, IDENTIFICATION SYSTEMS, RESEARCH MANAGEMENT, OPEN SYSTEM ARCHITECTURE, TECHNOLOGY ASSESSMENT
Identifiers: (U) IDENTITY MANAGEMENT
Abstract: (U) Government and industry have a common challenge in today's global society to provide more robust identity management tools, and identity governance principles on how to deploy these tools intelligently to meet national and international needs. Biometrics are the most definitive, real-time identity management tools currently available; however, use of the technology thus far has mainly consisted of systems designed to meet narrow objectives. To fully meet large-scale identity governance requirements, the use of biometrics technology must be made more robust, scalable and interoperable. Meeting these needs will require biometrics technology enhancements, adjustments of commercial business practices and system designs, and development of consensus on social, legal, privacy and policy considerations. Collaboration among the biometrics community government, industry and academia on these common challenges is essential. The NSTC Subcommittee on Biometrics developed this report to describe the major challenges that must be addressed by the biometrics community. Working together to overcome these challenges, the community will meet evolving operational requirements while being supported by a robust biometrics industry. This report highlights appropriate future roles for the federal government in advancing biometrics development to meet the needs of both our Nation and the broader worldwide community.
Biometric Collection, Transmission and Storage Standards. Version 1.1
Report Date: 24 Jul 2006
Descriptors: (U) *DATA MANAGEMENT, *STANDARDS, *BIOMETRY, *DATA TRANSMISSION SECURITY, *COLLECTION, DEPARTMENT OF DEFENSE, FINGERPRINTS, FACE(ANATOMY), DATA STORAGE SYSTEMS, IMAGES, FORMATS
Identifiers: (U) *BIOMETRICS, DISR(DEFENSE INFORMATION TECHNOLOGY STANDARDS REGISTRY)
Abstract: (U) This document provides a comprehensive technical reference that lists published biometric standards and describes their applicability to the biometric functions described in the Capstone Concept of Operations (CONOPS) for Department of Defense (DoD) Biometrics in Support of Identity Superiority. It was prepared by the DoD Biometrics Standards Working Group (BSWG) to assist in the development of future system-specific policy and technical documents, such as standard operating procedures, architecture technical views, and application profiles. This document provides support for a number of biometric modalities, including: fingerprints, face images, iris images, signature/sign data, hand geometry, and palm prints. It also describes the status of biometric standards in the DoD Information Technology Standards Registry. The appendices of this document contain a brief overview of the criteria for DoD adoption of standards and information on the collection of non-standardized biometric data, including DNA and voice recording samples. The DoD BSWG will update this document on a regular basis as new biometric standards emerge and to maintain consistency with the CONOPS.
Phrase-based Multimedia Information Extraction
Personal Author(s): Cohen, Eric, Tzoukermann, Evelyne,
Report Date: Jul 2006
Descriptors: (U) *SPEECH RECOGNITION, INFORMATION RETRIEVAL, EXTRACTION
Identifiers: (U) *INFORMATION EXTRACTION, *NAMED ENTITIES, *SR(SPEECH RECOGNITION), AUDIO EXTRACTION, TOPIC SEGMENTATION, TOPIC IDENTIFICATION, AUDIO CONTENT, VIDEO CONTENT, PE62805F, WUAFRL459E4DU1
Abstract: (U) StreamSage proposed to develop a prototype software system that would specifically deal with the two primary challenges of speech data on the performance of information extraction: degraded input data and the time-based nature of the content. In order to overcome these two challenges, this effort focused on two general areas: mitigating the degraded quality of speech data and improving entity identification. Technologies developed under this project for audio/video named entity identification and end user access to relevant information could have tremendous value for both military and commercial entities.
Personal Author(s): Diefenderfer, Graig T
Report Date: Jun 2006
Descriptors: (U) *MATCHING, *BIOMETRY, *FINGERPRINT RECOGNITION, *FINGERPRINTS, ALGORITHMS, INPUT, THESES, IMAGES, FILTERS
Identifiers: (U) MINUTIAE, THINNING
Abstract: (U) (maximum 200 words) The use of biometrics is an evolving component in today's society. Fingerprint recognition continues to be one of the most widely used biometric systems. This thesis explores the various steps present in a fingerprint recognition system. The study develops a working algorithm to extract fingerprint minutiae from an input fingerprint image. This stage incorporates a variety of image pre-processing steps necessary for accurate minutiae extraction and includes two different methods of ridge thinning. Next, it implements a procedure for matching sets of minutiae data. This process goes through all possible alignments of the datasets and returns the matching score for the best possible alignment. Finally, it conducts a series of matching experiments to compare the performance of the two different thinning methods considered. Results show that thinning by the central line method produces better False Non-match Rates and False Match Rates than those obtained through thinning by the block filter method.
Using Non-Orthogonal Iris Images for Iris Recognition
Personal Author(s): Gaunt, Ruth M
Report Date: 05 May 2006
Descriptors: (U) *IMAGES, *PATTERN RECOGNITION, *IRIS, DATA BASES, ALGORITHMS, SIGNAL PROCESSING, MODIFICATION, ORTHOGONALITY, IDENTIFICATION SYSTEMS, ONE DIMENSIONAL, ACCURACY, THREE DIMENSIONAL, TRANSFORMATIONS(MATHEMATICS)
Identifiers: (U) *NON-ORTHOGONAL RECOGNITION, BIOMETRICS
Abstract: (U) The iris is the colored portion of the eye that surrounds the pupil and controls the amount of light that can enter the eye. The variations within the patterns of the iris are unique between eyes, which allows for accurate identification of an individual. Current commercial iris recognition algorithms require an orthogonal image of the eye (subject is looking directly into a camera) to find circular inner (pupillary) and outer (limbic) boundaries of the iris. If the subject is looking away from the camera (non-orthogonal), the pupillary and limbic boundaries appear elliptical, which a commercial system may be unable to process. This elliptical appearance also reduces the amount of information that is available in the image used for recognition. These are major challenges in non-orthogonal iris recognition. This research addressed these issues and provided a means to perform non-orthogonal iris recognition. All objectives set forth at the start of this project were accomplished. The first major objective of this project was to construct a database of non-orthogonal iris images for algorithm development and testing. A collection station was built that allows for the capture of iris images at 0 degrees (orthogonal), 15 degrees, 30 degrees, and 45 degrees. During a single collection on an individual, nine images were collected at each angle for each eye. Images of approximately 90 irises were taken, with 36 images collected per eye. Sixty irises were evaluated twice, resulting in a total of almost 7100 images in the database. The second major objective involved modifying the Naval Academy's one-dimensional iris recognition algorithm so it could process non-orthogonal iris images. An elliptical-to-circular (affine) transformation was applied to the nonorthogonal images to create circular boundaries. This permitted the algorithm to be run as designed, with this modified algorithm used in the recognition testing phase of the project.
Identification - Friend or Foe? The Strategic Uses and Future Implications of the Revolutionary New ID Technologies
Personal Author(s): Pruett, Richard K
Report Date: 26 Apr 2006
Descriptors: (U) *IDENTIFICATION SYSTEMS, *COUNTERINSURGENCY, TRACKING, SURVEILLANCE, RISK MANAGEMENT, BIOMETRY, PUBLIC OPINION
Identifiers: (U) INFORMATION TECHNOLOGY, NATIONAL VALUES, IDENTIFICATION TECHNOLOGIES, PRIVACY, CIVIL LIBERTIES, RFID(RADIOFREQUENCY IDENTIFICATION), INFORMATION DOMINANCE, BIOMETRICS, NATIONAL POWER
Abstract: (U) Recent developments in identification (ID) technologies are likely to have a revolutionary impact on American society and the manner by which it wages war. The good news is that broader and more creative use of the new ID technologies could enable coalition forces to achieve dramatic victories in the Global War on Terrorism (GWOT) by targeting directly and effectively a critical requirement of most insurgencies: the insurgents' anonymity. The bad news is that these same technologies may be inherently inimical to the future of privacy and American civil liberties. They could transform our nation and others into surveillance societies concentrating in the hands of central governments levers of control without parallel in human history. How to reconcile American interests and values with the imperative to bend every element of national power in their defense is the central paradox of the GWOT. Are the new ID technologies useful means to the important end of securing the United States against potentially cataclysmic attacks or will they subvert the very interests and values at the core of all we seek to defend?
Thermal Face Recognition Over Time
Personal Author(s): Socolinsky, Diego A, Selinger, Andrea
Report Date: Jan 2006
Descriptors: (U) *IDENTIFICATION SYSTEMS, *FACE(ANATOMY), ALGORITHMS, THERMAL IMAGES, INFRARED IMAGES
Identifiers: (U) *FACE RECOGNITION
Abstract: (U) We present a comparative study of face recognition performance with visible and thermal infrared imagery, emphasizing the influence of time-lapse between enrollment and testing images. Most previous research in this area, with few exceptions, focused on results obtained when enrollment and testing images were acquired in the same session. We show that the performance difference between visible and thermal recognition in a time-lapse scenario is smaller than previously believed, and in fact is not statistically significant to existing data sets.
Network-Centric Maritime Radiation Awareness and Interdiction Experiments
Personal Author(s): Bordetsky, Alex, Dougan, Arden D, Nekoogar, Faranak
Report Date: Jan 2006
Descriptors: (U) *RADIATION, *COMMUNICATIONS NETWORKS, *COMMUNICATION AND RADIO SYSTEMS, *TERRORISM, *NETWORK TOPOLOGY, *RADIO TRANSMISSION, DATA BASES, WARFARE, TEST BEDS, DETECTORS, DISTRIBUTION, PROTOTYPES, IDENTIFICATION, CREWS, FINGERPRINTS, NARROWBAND, BIOMETRY, CHANNELS, TNT, SELECTION, UNMANNED, MISSIONS, LONG RANGE(DISTANCE), ELECTROMAGNETIC WAVE PROPAGATION, INTERDICTION, REAL TIME, UNDERWATER VEHICLES, GLOBAL, FILES(RECORDS)
Abstract: (U) The paper addresses technological and operational challenges of developing a global plug-and-play Maritime Domain Security testbed for the Global War on Terrorism mission. This joint NPS-LLNL project is based on the NPS Tactical Network Topology (TNT) comprised of long-haul OFDM networks combined with self-forming wireless mesh links to air, surface, ground, and underwater unmanned vehicles. This long-haul network is combined with ultra-wideband (UWB) communications systems for wireless communications in harsh radio propagation channels. LLNL s UWB communication prototypes are designed to overcome shortcomings of the present narrowband communications systems in heavy metallic and constricted corridors inside ships. In the center of our discussion are networking solutions for the Maritime Interdiction Operation (MIO) Experiments in which geographically distributed command centers and subject matter experts collaborate with the Boarding Party in real time to facilitate situational understanding and course of action selection. The most recent experiment conducted via the testbed extension to the Alameda Island exercised several key technologies aimed at improving MIO. These technologies included UWB communications from within the ship to Boarding Party leader sending data files and pictures, advanced radiation detection equipment for search and identification, biometric equipment to record and send fingerprint files to facilitate rapid positive identification of crew members, and the latest updates of the NPS Tactical Network Topology facilitating reachback to LLNL, Biometric Fusion Center, USCG, and DTRA experts.
On the Role of Object-Specific Features for Real World Object Recognition in Biological Vision
Personal Author(s): Serre, Thomas , Riesenhuber, Maximilian, Louie, Jennifer , Poggio, Tomaso
Report Date: Jan 2006
Descriptors: (U) *COMPUTER VISION, ALGORITHMS, PATTERN RECOGNITION, FACE(ANATOMY), VISUAL CORTEX, ARTIFICIAL INTELLIGENCE
Identifiers: (U) OBJECT RECOGNITION, FACE DETECTION, VISUAL FEATURES, HMAX MODEL, OBJECT-SPECIFIC FEATURES
Abstract: (U) Models of object recognition in cortex have so far been mostly applied to tasks involving the recognition of isolated objects presented on blank backgrounds. However, ultimately models of the visual system have to prove themselves in real world object recognition tasks. Here we took a first step in this direction: We investigated the performance of the HMAX model of object recognition in cortex recently presented by Riesenhuber & Poggio on the task of face detection using natural images. We found that the standard version of HMAX performs rather poorly on this task, due to the low specificity of the hardwired feature set of C2 units in the model (corresponding to neurons in intermediate visual area V4) that do not show any particular tuning for faces vs. background. We show how visual features of intermediate complexity can be learned in HMAX using a simple learning rule. Using this rule, HMAX outperforms a classical machine vision face detection system presented in the literature. This suggests an important role for the set of features in intermediate visual areas in object recognition.
Illumination Invariant Face Recognition Using Thermal Infrared Imagery
Personal Author(s): Socolinsky, Diego A, Wolff, Lawrence B, Neuheisel, Joshua D, Eveland, Christopher K
Report Date:Jan 2006
Descriptors: (U) *RECOGNITION, *THERMAL IMAGES, *FACE(ANATOMY), ALGORITHMS, EMISSION, COMPUTER VISION, SKIN(ANATOMY), INVARIANCE, ILLUMINATION, INFRARED IMAGES
Identifiers: (U) FACIAL RECOGNITION, THERMAL EMISSION, LWIR(LONG WAVE INFRARED), THERMAL INFRARED
Abstract: (U) A key problem for face recognition has been accurate identification under variable illumination conditions. Conventional video cameras sense reflected light so that image gray values are a product of both intrinsic skin reflectivity and external incident illumination, thus obfuscating the intrinsic reflectivity of skin. Thermal emission from skin, on the other hand, is an intrinsic measurement that can be isolated from external illumination. We examine the invariance of Long-Wave InfraRed (LWIR) imagery with respect to different illumination conditions from the viewpoint of performance comparisons of two well-known face recognition algorithms applied to LWIR and visible imagery. We develop rigorous data collection protocols that formalize face recognition analysis for computer vision in the thermal IR.
Appearance-Based Facial Recognition Using Visible and Thermal Imagery: A Comparative Study
Personal Author(s): Selinger, Andrea , Socolinsky, Diego A
Report Date: Jan 2006
Descriptors: (U) *IDENTIFICATION SYSTEMS, *FACE(ANATOMY), ALGORITHMS, METHODOLOGY, CALIBRATION, THERMAL IMAGES, FALSE ALARMS, INFRARED IMAGES
Identifiers: (U) *FACE RECOGNITION
Abstract: (U) We present a comprehensive performance analysis of multiple appearance-based face recognition methodologies, on visible and thermal infrared imagery. We compare algorithms within and between modalities in terms of recognition performance, false alarm rates and requirements to achieve specified performance levels. The effect of illumination conditions on recognition performance is emphasized, as it underlines the relative advantage of radiometrically calibrated thermal imagery for face recognition.
802.16 OFDM Rapidly Deployed Network for Near-Real-Time Collaboration of Expert Services in Maritime Security Operations
Personal Author(s): Marvin, Christopher E
Report Date: Sep 2005
Descriptors: (U) *DATA TRANSMISSION SYSTEMS, *COMMUNICATIONS NETWORKS, *COUNTERTERRORISM, *CARGO SHIPS, *FREQUENCY DIVISION MULTIPLEXING, *COLLABORATIVE TECHNIQUES, *WIRELESS LINKS, PORTABLE EQUIPMENT, REAL TIME, FIELD TESTS, CARGO, LAW ENFORCEMENT, HOMELAND SECURITY, SITUATIONAL AWARENESS, SMUGGLING, COAST GUARD, SHIPPING, TERRORISM, REMOTE DETECTION, MERCHANT VESSELS, SATELLITE COMMUNICATIONS, BROADBAND, THESES, NAVY, TEST BEDS
Identifiers: (U) *OFDM(ORTHOGONAL FREQUENCY DIVISION MULTIPLEXING), *MARITIME SECURITY, *VBSS(VISIT BOARD SEARCH AND SEIZURE), IEEE802.16, COMMON OPERATING PICTURE, TACTICAL NETWORK TOPOLOGY, LAWRENCE LIVERMORE NATIONAL LABORATORY, NATIONAL BIOMETRICS FUSION CENTER, INNOVATIVE SURVIVABILITY TECHNOLOGIES, ULTRA-WIDEBAND, EXPERT SERVICES REACH-BACK, ILLEGAL TRADE, ILLEGAL CARGO, ILLEGAL TRAFFICKING, NETWORK CENTRIC WARFARE, AN-50E, AN-50M, TNT 05-3, RADIATION DETECTION, VPN(VIRTUAL PRIVATE NETWORKS), BIOMETRIC FUSION
Abstract: (U) The world's shipping lanes are an area of intense focus in the Global War on Terror. Every day millions of tons of cargo are shipped through thousands of ports. Most cargo is harmless, however, some ships carry the weapons and human operators of terrorist organizations. To prevent the spread of weapons and terror suspects on the sea lanes, the cargo, passengers, and crew of these vessels must be subject to a level of scrutiny that is orders of magnitude greater than current efforts. The ability to rapidly extend a network and provide virtual expert services to Visit, Board, Search and Seizure (VBSS) boarding teams is crucial to protecting the United States and its allies from seaborne terror attacks and infiltration. This thesis uses scenario-based experimentation to examine the methods for implementing near-real-time collaborative work spaces in a virtual environment able to support VBSS operation anywhere in the world, limited only by network connectivity. The use of collaborative tools vastly increases the amount, type, and accuracy of information that can be processed. Radiation detection or classification and biometric fusion are among the hundreds of virtual collaborative sources that can be leveraged as force multipliers to bring network centric warfare to the maritime security domain.
Improved Network Security and Disguising TCP/IP Fingerprint through Dynamic Stack Modification
Personal Author(s): Judd, Aaron C
Report Date: Sep 2005
Descriptors: (U) *COMPUTERS, *OPERATING SYSTEMS(COMPUTERS), *COMPUTER NETWORKS, *COMPUTER ACCESS CONTROL, *FINGERPRINTS, MODIFICATION, COMPUTER CRIMES, COMMUNICATIONS PROTOCOLS, FINGERPRINT RECOGNITION, ATTACK, VULNERABILITY, THESES
Identifiers: (U) FINGERPRINT MODIFICATION, LINUX OPERATING SYSTEM, WINDOWS OPERATING SYSTEM, NETWORK SECURITY, OS FINGERPRINTING, TCP/IP(TRANSMISSION CONTROL PROTOCOL/INTERNET PROTOCOL), DYNAMIC STACK MODIFICATION
Abstract: (U) Each computer on a network has an Operating System (OS) Fingerprint that can be collected through various applications. Because of the complexity of network systems, vulnerabilities and exploitations of the same to gain access to systems will always be a problem. Those wishing to attack a system can use the OS Fingerprint to identify the types of vulnerabilities and software exploits that will be effective against the system. This paper discusses how system vulnerabilities become exploited and used by network attackers. Because OS Fingerprints are one of many tools network attackers will use to identify and attack a system, concealing a system's OS Fingerprint becomes an important part of securing the system. To demonstrate the capability of concealing the OS Fingerprint of a system, a prototype system was developed. This prototype changed the OS Fingerprint of a Linux system so that it matched a Windows NT system.
Proof of Concept: Iraqi Enrollment via Voice Authentication Project
Personal Author(s): Lee, Samuel K
Report Date:Sep 2005
Descriptors: (U) *MILITARY OPERATIONS, *IRAQ, *SPEECH RECOGNITION, *VERIFICATION, *SPEECH, *VOICE COMMUNICATIONS, WARFARE, COMBAT EFFECTIVENESS, COMBAT READINESS, RESEARCH MANAGEMENT, NORTH AMERICA, BIOMETRY, SPEECH ANALYSIS, PILOTS, THESES, SCHEDULING, JOINT MILITARY ACTIVITIES, COMMERCIAL EQUIPMENT, LANGUAGE
Identifiers: (U) *PROOF OF CONCEPT, *VOICE AUTHENTICATION, *IRAQI ENROLLMENT VIA VOICE AUTHENTICATION PROJECT, IEVAP(IRAQI ENROLLMENT VIA VOICE AUTHENTICATION PROJECT), SPEAKER VERIFICATION TECHNOLOGY, VOICE BIOMETRICS, WARFIGHTING CAPABILITIES, NUANCE CALLER AUTHENTICATION 1.0, BIOMETRICS, AUTOMATIC SPEECH RECOGNITION
Abstract: (U) This thesis documents the findings of the Naval Postgraduate School (NPS) research team's efforts on the initial phase of the Iraqi Enrollment via Voice Authentication Project (IEVAP). The IEVAP is an Office of the Secretary of Defense sponsored research project commissioned to study the feasibility of speaker verification technology in support of the Global War on Terrorism security requirements. The intent of this project is to contribute toward the future employment of speech technologies in a variety of coalition military operations by developing a pilot proof-of-concept system that integrates speaker verification and automated speech recognition technology into a mobile platform to enhance warfighting capabilities. In this first phase of the IEVAP, NPS developed with the assistance of Nuance Communications, Inc. and the Defense Language Institute, a bilingual (English and Jordanian-Arabic) speech application that demonstrates the viability of speaker verification technology for use in operations in Iraq. Additionally, NPS conducted a test to assess the accuracy claim of Nuance's packaged speaker verification application, Nuance Caller Authentication 1.0 (for North American English). The NPS test consisted of 68 speaker enrollments and 411 speaker verification attempts. Upon completion of the test, NPS conducted a single data-point analysis yielding a system accuracy of 95.87%.
Experiments in Expression Recognition
Personal Author(s): Skelley, James P
Report Date: 16 Aug 2005
Descriptors: (U) *IMAGE PROCESSING, *PATTERN RECOGNITION, *FACE(ANATOMY), DATA BASES, MATRICES(MATHEMATICS), MAN COMPUTER INTERFACE, THESES, ALGORITHMS
Identifiers: (U) *EXPRESSION RECOGNITION, *EXPRESSION DATABASES, *OPTICAL FLOW, *SVM(SUPPORT VECTOR MACHINES), MMI(MAN MACHINE INTERFACES), FACIAL EXPRESSIONS, TEXTURE-VALUE FEATURES
Abstract: (U) Despite the significant effort devoted to methods for expression recognition, suitable training and test databases designed explicitly for expression research have been largely neglected. Additionally, possible techniques for expression recognition within an Man-Machine-Interface (MMI) domain are numerous, but it remains unclear what methods are most effective for expression recognition. In response, this thesis describes the means by which an appropriate expression database has been generated and then enumerates the results of five different recognition methods as applied to that database. An analysis of the results of these experiments is given, and conclusions for future research based upon these results is put forth.
Composite Signature Based Watermarking for Fingerprint Authentication
Personal Author(s): Ahmed, Farid , Moskowitz, Ira S
Report Date: 09 Aug 2005
Descriptors: (U) *BIOMETRIC SECURITY, FOURIER TRANSFORMATION, SYMPOSIA, INFORMATION ASSURANCE, DIGITAL FILTERS, FINGERPRINTS
Identifiers: (U) COMPOSITE FILTER, PHASE ONLY FILTER, DIGITAL WATERMARKING, DRM(DIGITAL RIGHTS MANAGEMENT), BIOMETRIC AUTHENTICATION
Abstract: (U) Digital watermarking is a technology to hide information in digital media. We extend the digital watermarking technique Phasemark(trademark), originally developed solely for image authentication, to biometrics to assist in forensic analysis. Using a signature extracted from the Fourier phase of the original image, we hide an encoded signature back into the original image forming a watermarked image. The hiding occurs in the Fourier transform frequency domain. The detection process computes the Fourier transform of the watermarked images, extracts the embedded signature and then correlates it with a calculated signature. Various correlation metrics determine the identity degree of biometric authentication. We show how a composite filter can be used in conjunction with Phasemark(trademark) for robust authentication of fingerprints.
Border Security: The Role of the U.S. Border Patrol
Personal Author(s): Nunez-Neto, Blas
Report Date: 10 May 2005
Descriptors: (U) *TERRORISTS, *UNITED STATES GOVERNMENT, *STRATEGY, *BOUNDARIES, *AREA SECURITY, *ILLEGAL IMMIGRANTS, *HOMELAND SECURITY, DATA BASES, DETECTION, PREVENTION, LAW ENFORCEMENT, BIOMETRIC SECURITY, DRUG SMUGGLING, MEXICO, DETERRENCE, COOPERATION, LEGISLATION, MASS DESTRUCTION WEAPONS, MANPOWER, THREATS, INTERDICTION, VULNERABILITY, CANADA
Identifiers: (U) *BORDER PATROL, *BORDER SECURITY, USBP(UNITED STATES BORDER PATROL), HOMELAND SECURITY ACT, DHS(DEPARTMENT OF HOMELAND SECURITY), IBET(INTEGRATED BORDER ENFORCEMENT TEAMS), NORTHERN BORDER, SOUTHWEST BORDER, ILLEGAL ALIENS, CRIMINALS, IDENT(AUTOMATED BIOMETRIC FINGERPRINT IDENTIFICATION SYSTEM), IAFIS(INTEGRATED AUTOMATED FINGERPRINT IDENTIFICATION SYSTEM), ABC(ARIZONA BORDER CONTROL), HUMAN SMUGGLING, INTERAGENCY COORDINATION, MIGRANT DEATHS, ASI(AMERICA'S SHIELD INITIATIVE), BSI(BORDER SAFETY INITIATIVE), BORDER APPREHENSIONS, TERRORIST SCREENING, AGENT ATTRITION, CIVILIAN GROUPS
Abstract: (U) The United States Border Patrol (USBP) has a long and storied history as the nation's first line of defense against unauthorized migration. Today, the USBP's primary mission is to detect and prevent the entry of terrorists, weapons of mass destruction, and illegal aliens into the country, and to interdict drug smugglers and other criminals along the border. The Homeland Security Act of 2002 dissolved the Immigration and Naturalization Service and placed the USBP within the Department of Homeland Security (DHS). During the last decade, the USBP has seen its budget and manpower more than triple. This expansion was the direct result of Congressional concerns about illegal immigration and the agency's adoption of "Prevention Through Deterrence" as its chief operational strategy in 1994. The strategy called for placing USBP resources and manpower directly at the areas of greatest illegal immigration to detect, deter, and apprehend aliens attempting to cross the border between official points of entry. Post 9/11, the USBP refocused its strategy on preventing the entry of terrorists and weapons of mass destruction, as laid out in its recently released National Strategy. There are significant geographic, political, and immigration-related differences between the Northern border with Canada and the Southwest border with Mexico. Accordingly, the USBP deploys a different mix of personnel and resources along the two borders. Some issues for Congress to consider could include the slow rate of integration between the USBP's biometric database of illegal aliens and the Federal Bureau of Investigation's (FBI) biometric database of criminals and terrorists; the number of unauthorized aliens who die attempting to enter the country each year; the organized human smuggling rings that have proliferated as entering the country has become more difficult; and the threat posed by terrorists along the sparsely defended Northern border as well as the more porous Southwest border.
Non-Orthogonal Iris Segmentation
Personal Author(s): Bonney, Bradford L
Report Date: 09 May 2005
Descriptors: (U) *PATTERN RECOGNITION, *IRIS, DATA BASES, ALGORITHMS, ORTHOGONALITY, EYE PIGMENTS, EYE, DIGITAL SYSTEMS
Identifiers: (U) TRIDENT SCHOLAR PROJECT
Abstract: (U) The goal of this Trident Scholar project was to isolate the iris, the colored part of the eye, in a non-orthogonal, digital image of the human eye. A non-orthogonal image is an image where the eye is not looking directly at the camera. Iris pattern differs significantly between individuals (including identical twins) which allows for its use as an accurate biometric identifier. Both commercial and iris recognition system are becoming widespread in government and industry for logical security and access control. These iris recognition systems assume that captured iris are images are normal, or orthogonal, to the sensing devices and therefore search for circular patterns in the image. Off-angle, or non-orthogonal, images of irises cannot currently be used for identification because the iris appears elliptical; commercial algorithms cannot isolate an elliptical iris in order to start the identification process. This research expanded the functionality of iris recognition technology by developing a set of new algorithms to isolate a non- orthogonal iris in a digital image. The algorithmic approach to first isolate the pupil, the dark portion in the center of the eye. The pupil was isolated using bit-plane processing. The pupil appeared as a large homogenous region surrounded by insignificant noise, which allowed for easy definition of the pupil-iris boundary. Next, the limbic boundary (the outer edge of the iris) was determined in the cardinal directions and an ellipse was calculated that incorporated those points. After all boundaries were calculated, an "iris mask" was created to identify pixels in the image that contained the iris data, the only pixels of value for the identification of an individual. The functionality of the algorithm was tested using a database collected at the United States Naval Academy. Both orthogonal and non-orthogonal iris images were used to collect quantitative results.
Field Collection and Analysis of Forensic and Biometric Evidence Associated with IEDs
Personal Author(s): Prather, Mark
Report Date: 02 May 2005
Descriptors: (U) *EXPLOSIVE CHARGES, *EXPLOSIVES DETECTION, VAPORS, FIELD TESTS, ADMINISTRATIVE PERSONNEL, CLOTHING, BIOMETRY, BOMBER AIRCRAFT, EXPLOSIVE ORDNANCE DISPOSAL, HANDS, HAIR
Identifiers: (U) SBIR(SMALL BUSINESS INNOVATION RESEARCH), SBIR REPORTS, SBIR TOPIC N04-901 PHASE 1, IED(IMPROVISED EXPLOSIVE DEVICES), SUICIDE BOMBERS
Abstract: (U) This report summarizes the results for contract N00014-05-M-0010. In summary, the objectives of this work were: * Define sample collection scenarios that are suited for the screening of personnel who are likely to be involved in the production of improvised explosive devices (IEDs) or who may be suicide bombers, to include at least one swab approach and one vapor sampling of hands or clothing. * Optimize the Fido technology to provide sample analysis in support of the defined scenarios. * Demonstrate successful detection within the scenarios. * Characterize samples of explosives with Fido and demonstrate the ability to determine probable matches to other samples. * Demonstrate Fido as a detection tool for other forensics applications, such as the detection of explosives in hair samples. Methods for collection of forensics evidence from humans and surfaces of objects that may have been exposed to explosives in the course of storage, construction, transport, and deployment of IEDs have been developed. These methods were been demonstrated with very encouraging results during laboratory and field trials. During field trials conducted at the Countermine Facility (CM) and the Joint Experimental Research Complex (JERC) site at Yuma Proving Grounds (YPG) from December 13-17, 2004, detection of explosives on explosive ordnance disposal (EOD) technicians who had recently assembled similated IEDs was demonstrated with a high degree of probability. In addition, detection of explosives on vehicles used to transport the IEDs was demonstrated. Persons (mainly administrators at YPG) were also included in the study as persons who do not handle explosives (i.e., as blank' controls). With the exception of one individual, no sensor response to blank' individuals was noted. Contamination of facilities routinely utilized by EOD technicians at the CM site was also demonstrated.
Science and Technology: A Foundation for Homeland Security
Personal Author(s): Marburger, III, John H
Report Date: Apr 2005
Descriptors: (U) *STRATEGY, *PROTECTION, *MASS DESTRUCTION WEAPONS, *COUNTERTERRORISM, *COUNTERMEASURES, *HOMELAND SECURITY, NUCLEAR WEAPONS, RADIOACTIVE MATERIALS, CHEMICAL AGENT DETECTORS, BIOLOGICAL AGENT DETECTORS, FIRST RESPONDERS, BIOMETRIC SECURITY, CHEMICAL AGENT TERRORISM, BIOTERRORISM, SCIENTIFIC RESEARCH, EARLY WARNING SYSTEMS, AGRICULTURE, MEDICAL RESEARCH, LABORATORIES, STANDARDS, THREATS, UNITED STATES GOVERNMENT
Identifiers: (U) *SCIENCE AND TECHNOLOGY, RADIOLOGICAL COUNTERMEASURES, NUCLEAR COUNTERMEASURES, MEDICAL COUNTERMEASURES, AGRICULTURE PROTECTION, FIRST RESPONDER CAPABILITIES, RESEARCH COORDINATION, LABORATORY NETWORKS, RAPID PROTOTYPING, BORDER SECURITY, AIRPORT SECURITY, SEAPORT SECURITY, NUCLEAR DETECTION EQUIPMENT, PROJECT BIOWATCH, PROJECT BIOSHIELD, GEORGE W BUSH ADMINISTRATION
Abstract: (U) The United States has made significant strides to protect the homeland since the terrorist attacks of September 11, 2001. Since those tragic events, the Federal Government has responded in numerous ways to protect against future attacks. Science and technology (S&T) have played a vital part in the progress made to date, and will continue to inform and enhance the country's homeland security efforts. "Science and Technology: A Foundation for Homeland Security" details the numerous accomplishments of S&T that have helped to secure the homeland. This report builds upon the "National Strategy for Homeland Security," released by the President on July 16, 2002, which set forth a sound framework to reduce America's vulnerability and to respond with improved agility and effectiveness to future terrorist attacks. Since that time, much has been accomplished, and still more has been initiated. Some key accomplishments highlighted in this document are as follows: (1) Bolstering border security through the development and deployment of nuclear detection equipment along the U.S. border, airports, and seaports to detect, deter, and ultimately prevent the trafficking of nuclear and radioactive materials; (2) Providing an early warning system for bio-threats through Project BioWatch, a cooperative effort among the Department of Homeland Security, the Environmental Protection Agency, and the Centers for Disease Control and Prevention Laboratory Response Network; and (3) Speeding development and procurement of new medical countermeasures against current and future chemical, biological, radiological, and nuclear terrorist threats through Project BioShield, an initiative signed into law by the President in July 2004. Although by no means exhaustive, the efforts described in this report typify the progress that has been made in the key research areas designated as priority goals by the George W. Bush Administration in the "National Strategy.
Fusion of Dependent and Independent Biometric Information Sources
Personal Author(s): Huang, Dongliang, Leung, Henry, Li, Winston
Report Date: Mar 2005
Descriptors: (U) *DATA FUSION, *BIOMETRY, COMPUTERIZED SIMULATION, DECISION MAKING, INFORMATION SYSTEMS, CANADA, COMPUTER ARCHITECTURE, MULTIMODE
Identifiers: (U) FOREIGN REPORTS, AQ F06-02-0646, INFORMATION FUSION, BIOMETRICS, DEPENDENT, INDEPENDENT, SIGNAL FUSION, FEATURE FUSION, DECISION FUSION
Abstract: (U) In this report, an overview of information fusion techniques for dependent and independent sources, specifically for biometric applications, is provided. The information fusion architecture is presented for both dependent and independent sources addressing in detail the various fusion techniques at four different levels namely: raw data or signal level, feature level, decision level and multi-level integrated fusion. Furthermore, the report addresses the question of whether independent biometric sources can be fused to provide multi-modal biometric system with enhanced performance. The report shows that even when the sources are independent, the performance of a multi-modal biometric system can be better than that of a biometric system based on single source. The performance is measured in terms of total false accept rate (FAR) and false rejection rate (FRR). The conditions for achieving an improved performance for the decision level fusion using AND, OK and majority voting are derived theoretically and confirmed through computer simulations.
An Analysis of Biometric Technology as an Enabler to Information Assurance
Personal Author(s): Deschaine, Darren A
Report Date: 01 Mar 2005
Descriptors: (U) *DEPARTMENT OF DEFENSE, *MILITARY APPLICATIONS, *BIOMETRY, *BIOMETRIC SECURITY, *INFORMATION ASSURANCE, UNITED STATES, THESES, LIMITATIONS, HISTORY, SPEECH RECOGNITION, PATTERN RECOGNITION, RETINA, HANDS, FACE(ANATOMY), HANDWRITING, FINGERPRINT RECOGNITION, IRIS, VOICEPRINTS, INFORMATION SECURITY
Identifiers: (U) HAND GEOMETRY, IRIS SCANS, RETINA SCANS, FACIAL RECOGNITION, VOICE RECOGNITION, SIGNATURE RECOGNITION, INFORMATION OPERATIONS, HISTORICAL RESEARCH METHODOLOGY, HISTORIOGRAPHY
Abstract: (U) The use of and dependence on, Information technology (IT) has grown tremendously in the last two decades. Still, some believe the United States is only in the infancy of this growth. This explosive growth has opened the door to capabilities that were only dreamed of in the past. As easy as it is to see how advantageous this technology is, it also is clear that with its advantages come distinct responsibilities and new problems that must be addressed. For instance, the minute one begins using information processing systems, the world of information assurance (IA) becomes far more complex. As a result, the push for better IA is necessary. To reach this increased level of IA, a further dependence on technology has developed. As an example, the field of biometrics has matured and has become an enabler to the U.S. Department of Defense IA model.
Automatically Log Off Upon Disappearance of Facial Image
Personal Author(s): Yang, Xue D, Kort, Peter, Dosselmann, Richard
Report Date: Mar 2005
Descriptors: (U) *FACE(ANATOMY), *COMPUTER ACCESS CONTROL, *INTRUSION DETECTION(COMPUTERS), *BIOMETRIC SECURITY, ALGORITHMS, IMAGE PROCESSING, CHANGE DETECTION, NEURAL NETS, CANADA
Identifiers: (U) FACE DETECTION, FOREIGN REPORTS
Abstract: (U) The ability to prevent unauthorized users from gaining access to classified or sensitive data is crucial to many organizations, especially the military. There has been significantly increased attention in recent years in biometrics technology in order to provide more secured access controls to information systems. Different technologies and various products have been developed to authenticate users at entrances. However, once a user has logged on to a system, there is currently no mechanism to monitor the user's identity. It is important to ensure that the user, throughout the communication, is the authorized user for high-security applications. The objective of this project is to develop a demonstration system that will automatically log off a PC when the user's face disappears for an adjustable time interval. In this report, a brief overview of face detection technologies is provided. The particular neural network-based face detection algorithm employed in the demo system is discussed in more detail. It is followed by the design of the demo system, and discussion of technical issues encountered during the development.
Biometric Identifiers and Border Security: 9/11 Commission Recommendations and Related Issues
Personal Author(s): Morgan, Daniel, Krouse, William
Report Date: 07 Feb 2005
Descriptors: (U) *UNITED STATES, *BOUNDARIES, *COUNTERTERRORISM, *BIOMETRIC SECURITY, *HOMELAND SECURITY, DATA BASES, TERRORISTS, INSPECTION, LEGISLATION, BIOMETRY, FINGERPRINT RECOGNITION, IRIS, FACE(ANATOMY), LAW ENFORCEMENT, PATTERN RECOGNITION, STANDARDS, COSTS, ACCURACY, DIGITAL SYSTEMS
Identifiers: (U) *BORDER SECURITY, *BIOMETRIC TECHNOLOGIES, BORDER INSPECTIONS, BIOMETRIC PASSPORTS, ENTRY EXIT SCREENING, ENTRY EXIT CONTROL, US-VISIT(UNITED STATES VISITOR AND IMMIGRANT STATUS INDICATOR TECHNOLOGY PROGRAM), BIOMETRIC SCREENING SYSTEMS, FACIAL RECOGNITION, IRIS SCANS, HAND GEOMETRY, IAFIS(INTEGRATED AUTOMATED FINGERPRINT IDENTIFICATION SYSTEM), IDENT(AUTOMATED BIOMETRIC FINGERPRINT IDENTIFICATION SYSTEM), NSEERS(NATIONAL SECURITY ENTRY-EXIT REGISTRATION SYSTEM), CCD(CONSULAR CONSOLIDATED DATABASE), BORDER SECURITY ACT
Abstract: (U) In its final report, the 9/11 Commission concluded that funding and completing a "biometric entry-exit screening system" for travelers to and from the United States is essential to U.S. national security. The commission noted that the United States has built the first phase of a biometric screening system known as US-VISIT, and recommended that the "patchwork" of other border screening systems be consolidated with US-VISIT to serve as the basis for a single system to streamline border inspections. This report provides an overview of biometric technologies and the major U.S. biometric border screening systems, including US-VISIT, and discusses issues such as cost, performance, and user acceptance. Based in part upon the commission's recommendations, Congress included biometric provisions related to entry/exit control in the Intelligence Reform and Terrorism Prevention Act of 2004 (P.L. 108-458). This topic will probably continue to be of interest to the 109th Congress. This report will be updated as needed.
Security Threat Assessments for Hazmat Drivers
Personal Author(s): Rothberg, Paul F
Report Date: 25 Jan 2005
Descriptors: (U) *POLICIES, *LAND TRANSPORTATION, *THREAT EVALUATION, *HAZARDOUS MATERIALS, *DOMESTIC TERRORISM, *HOMELAND SECURITY, *DRIVERS(PERSONNEL), DATA BASES, CANADA, MEXICO, FINGERPRINT RECOGNITION, STATE GOVERNMENT, LEGISLATION, COUNTERTERRORISM, COSTS, VULNERABILITY, UNITED STATES GOVERNMENT
Identifiers: (U) TSA(TRANSPORTATION SECURITY ADMINISTRATION), *SECURITY THREAT ASSESSMENTS, *CDL(COMMERCIAL DRIVERS LICENSE), HAZMAT DRIVERS, DRIVER ASSESSMENTS, DRIVER LICENSING, CRIMINAL HISTORY CHECKS, IMMIGRATION CHECKS, INTELLIGENCE CHECKS, HAZMAT TRANSPORTATION
Abstract: (U) The Transportation Security Administration (TSA) is gradually implementing Section 1012 of the USA PATRIOT Act (P.L. 107-56). This provision seeks to reduce some of the security risks associated with hazardous materials (hazmat) transportation by requiring a security threat assessment of drivers with a hazmat endorsement on their commercial drivers license (CDL). This process, which includes immigration and database checks, may deter a terrorist from obtaining or keeping such an endorsement; nevertheless, the hazmat transportation system remains vulnerable to attack. Members of Congress are overseeing implementation of TSA's program, reviewing its financial impacts, and deciding whether to explicitly require in law a comparable review of Canadian- and Mexican-domiciled drivers transporting specified hazmats into the United States. During 2004, TSA screened 2.7 million drivers with a hazmat endorsement by comparing their names to those on databases. These checks generated more than 100 leads that were sent to the FBI. TSA recognizes that the reliability of this process will be improved by incorporating a fingerprint-based criminal background check. For each of the next 5 years, TSA will put roughly 1/5 of the drivers with, or seeking, a hazmat endorsement through a more comprehensive threat assessment process, including a fingerprint-based records review. TSA and the states have faced many challenges in the development and implementation of this initiative. The complete program was originally planned to start in 2003, however, it has been delayed several times. Starting January 31, 2005, TSA will not permit a state to issue a new hazmat endorsement with a CDL until a determination has been made that an applicant does not pose a security threat. Starting May 31, 2005, this TSA rule also applies to drivers seeking either to renew a CDL with this endorsement, or, in some cases, to transfer his/her license from one state to another.
On Multi-Scale Differential Features for Face Recognition
Personal Author(s): Ravela, S, Hanson, Allen R
Report Date: Jan 2005
Descriptors: (U) *ELECTRONIC EQUIPMENT, *IDENTIFICATION SYSTEMS, *FACE(ANATOMY), ALGORITHMS, STATISTICAL PROCESSES, ACCURACY, PERFORMANCE(ENGINEERING)
Identifiers: (U) *FACE RECOGNITION
Abstract: (U) This paper describes an algorithm that uses multi-scale Gaussian differential features (MGDFs) for face recognition. Results on standard sets indicate at least 96% recognition accuracy, and a comparable or better performance with other well known techniques. The MGDF based technique is very general; its original application included similarity retrieval in textures, trademarks, binary shapes and heterogeneous gray-level collections.
Infrared Imaging Face Recognition Using Nonlinear Kernel-Based Classifiers
Personal Author(s):Domboulas, Dimitrios I
Report Date: Dec 2004
Descriptors: (U) *IMAGE PROCESSING, *INFRARED IMAGES, *CLASSIFICATION, *PATTERN RECOGNITION, *FACE(ANATOMY), *BIOMETRIC SECURITY, DATA BASES, ALGORITHMS, LINEAR SYSTEMS, LOW COSTS, PERFORMANCE(ENGINEERING), EIGENVECTORS, THESES, NONLINEAR SYSTEMS, LOW RESOLUTION, LINEAR ALGEBRA, INFRARED CAMERAS
Identifiers: (U) *FACE RECOGNITION, *KERNAL BASED CLASSIFIERS, GDA(GENERALIZED DISCRIMINANT ANALYSIS), LINEAR CLASSIFICATION ALGORITHMS, NONLINEAR CLASSIFICATION ALGORITHMS, PCA(PRINCIPLE COMPONENT ANALYSIS), SVM(SUPPORT VECTOR MACHINES), UNCOOLED INFRARED IMAGERY, FISHERFACE CLASSIFIERS, NONLINEAR ALGEBRA
Abstract: (U) In recent years there has been an increased interest in effective individual control and enhanced security measures, and face recognition schemes play an important role in this increasing market. In the past, most face recognition research studies have been conducted with visible imaging data. Only recently have IR imaging face recognition studies been reported for wide use applications, as uncooled IR imaging technology has improved to the point where the resolution of these much cheaper cameras closely approaches that of their cooled counterparts. This study is part of ongoing research conducted at the Naval Postgraduate School that investigates the feasibility of applying a low-cost, uncooled IR camera for face recognition applications. This specific study investigates whether nonlinear kernel-based classifiers may improve overall classification rates over those obtained with linear classification schemes. The study is applied to a 50-subject IR database developed inhouse with a low-resolution, uncooled IR camera. Results show best overall mean classification performances around 98.55%, which represents a 5% performance improvement over the best linear classifier results obtained previously on the same database. The study also considers several metrics to evaluate the impacts variations in various user-specified parameters have on the resulting classification performances. These results show that a low-cost, low-resolution IR camera combined with an efficient classifier can play an effective role in security-related applications.
Automatic Gait Recognition for Human ID at a Distance
Personal Author(s): Nixon, Mark S, Carter, John N
Report Date: Nov 2004
Descriptors: (U) *DATA BASES, *COMPUTER VISION, *BIOMETRY, IMAGE PROCESSING, SCENARIOS, EUROPE, SPATIAL DISTRIBUTION, COVARIANCE, BIOMECHANICS, RANGE(DISTANCE), METHODOLOGY, HUMANS, WALKING, MOTION, SEQUENCES
Abstract: (U) Recognising people by their gait is a biometric of increasing interest. Now, analysis has progressed from evaluation by few techniques on small databases with encouraging results to large databases and still with encouraging results. The potential of gait as a biometric was encouraged by the considerable amount of evidence available, especially in biomechanics and literature. This report describes research within the Human ID (HiD) at a Distance program sponsored by the Defense Advanced Projects Research Agency through the European Research Office of the U.S. Army at the University of Southampton from 2000-2004. The research program was essentially designed to explore the capability of basic of gait as a biometric and potential for translation from a laboratory to a real world scenario. By development of specialized databases, by development of new techniques and by evaluation of laboratory and real-world data we contend that these objectives have indeed been achieved. There is a considerable volume of subsidiary developments not just of new computer vision techniques but also of approaches for spatiotemporal image analysis, particularly targeted at the modeling and understanding of human movement through image sequences. The ongoing interest in gait in a biometric is in a large part the wider remit of the analysis of human motion by computer vision techniques and due to the capability of gait as a biometric, as demonstrated by the results achieved by the HiD program
Prevention or Identification of Web Intrusion via Human Computer Interaction Behaviour - A Proposal
Personal Author(s): Gamboa, Hugo, Fred, Ana, Vieira, Antonio A
Report Date: 25 Oct 2004
Descriptors: (U) *MONITORING, *INTERACTIONS, *INTERNET, *BIOMETRIC SECURITY, SYMPOSIA, INTRUSION DETECTION(COMPUTERS), PORTUGAL, RECOGNITION, ACQUISITION
Identifiers: (U) *USER BEHAVIOR, *WIDAM(WEB INTERACTION DISPLAY AND MONITORING), *AUTHENTICATION, COMPONENT REPORTS, FOREIGN REPORTS, NATO FURNISHED, HUMAN COMPUTER INTERACTION
Abstract: (U) The present work proposes a new technique for the identification or prevention of intrusion in web applications via the monitoring of the user interaction behaviour. We report preliminary results in a verification task based on a user claiming his identity and being accepted or detected as an intruder after some time of user interaction monitoring. We describe the acquisition system that enables the remote monitoring of the user human computer interaction and the recognition system that detects an intrusion in the system, and present some preliminary results.
Face Detection and Recognition
Personal Author(s): Jain, Anil K
Report Date: 16 Aug 2004
Descriptors: (U) *DATA BASES, *DETECTION, *DEMOGRAPHY, *THREE DIMENSIONAL, *PATTERN RECOGNITION, *FACE(ANATOMY), *FEATURE EXTRACTION, ALGORITHMS, TRAINING, TWO DIMENSIONAL, ACCURACY, ILLUMINATION, COLORS, IMAGES, CLASSIFICATION, BACKGROUND, ETHNIC GROUPS, BIOMETRY
Identifiers: (U) *FACE RECOGNITION, *FACE DETECTION, FACE MATCHING, COLOR IMAGES, FACIAL POSES, FACIAL EXPRESSIONS, LIGHTING CONDITIONS, ETHNICITY CLASSIFICATION, GENDER CLASSIFICATION, 3D FACE MODELS, BIOMETRIC IDENTIFICATION
Abstract: (U) This report describes research efforts towards developing algorithms for a robust face recognition system to overcome many of the limitations found in existing two-dimensional facial recognition systems. Specifically, the report addresses the problem of detecting faces in color images in the presence of various lighting conditions and complex backgrounds as well as recognizing faces under variations in pose, lighting, and expression. The report is organized in two main parts: face detection and face recognition. A near real-time face detection system was developed that uses a skin-tone color model and facial features. For face recognition, the authors have developed four independent solutions: (1) evidence accumulation for 2D face recognition, (2) demographic information extraction from 2D facial images, (3) 3D-model enhanced 2D face recognition with a small number of training samples, and (4) 3D face recognition.
Infrared Face Recognition
Personal Author(s): Lee, Colin K
Report Date: Jun 2004
Descriptors: (U) *IMAGE PROCESSING, *INFRARED IMAGES, *FACE(ANATOMY), INFRARED DETECTION, EIGENVECTORS, THESES, CLASSIFICATION, IDENTIFICATION SYSTEMS, RECOGNITION, INFRARED CAMERAS
Identifiers: (U) PCA(PRINCIPAL COMPONENT ANALYSIS), LDA(LINEAR DISCRIMINANT ANALYSIS), FISHER LINEAR DISCRIMINANT ANALYSIS, SVD(SINGULAR VALUE DECOMPOSITION)
Abstract: (U) This study continues a previous face recognition investigation using uncooled infrared technology. The database developed in an earlier study is further expanded to include 50 volunteers with 30 facial images from each subject. The automatic image reduction method reduces the pixel size of each image from 160x120 to 60x45 . The study reexamines two linear classification methods: the Principal Component Analysis (PCA) and Fisher Linear Discriminant Analysis (LDA). Both PCA and LDA apply eigenvectors and eigenvalues concepts. In addition, the Singular Value Decomposition based Snapshot method is applied to decrease the computational load. The K-fold Cross Validation is applied to estimate classification performances. Results indicate that the best PCA-based method (using all eigenvectors) produces an average classification performance equal to 79.22%. Incorporated with PCA for dimension reduction, the LDA-based method achieves 94.58% accuracy in average classification performance. Additional testing on unfocused images produces no significant impact on the overall classification performance. Overall results again confirm uncooled IR imaging can be used to identify individual subjects in a constrained indoor environment.
Super-Resolution Still and Video Reconstruction from MPEG Coded Video
Personal Author(s): Altunbasak, Yucel
Report Date: 31 May 2004
Descriptors: (U) *DISCRETE FOURIER TRANSFORMS, SIGNAL PROCESSING, CODING, COEFFICIENTS, BAYES THEOREM, VIDEO SIGNALS, FREQUENCY STANDARDS
Identifiers: (U) DCT(DISCRETE COSINE TRANSFORM), DOMAIN BAYESIAN SUPERRESOLUTION, MPEG(MOVING PICTURE EXPERTS GROUP), VIDEO FACE RECOGNITION, IMAGE RECONSTRUCTION, HYSPECTRAL IMAGES
Abstract: (U) Transform coding is a popular and effective compression method for both still images and video sequences, as is evident from its widespread use in international media coding standards such as MPEG, H.263 and JPEG. The motion-compensated image (or the image itself) is divided into blocks and each block is independently transformed by a 2-D orthogonal transform to achieve energy compaction. The most commonly used transform is the discrete cosine transform (DCT). After the block transform, the transform coefficients undergo a quantization step. At low bit-rates, the DCT coefficients are coarsely quantized. This coarse quantization with independent quantization of neighboring blocks gives rise to blocking artifacts visible block boundaries.
Biometric Fusion Demonstration System Scientific Report
Personal Author(s): Mak, Mcken, Kim, Joseph, Thieme, Michael
Report Date: Mar 2004
Descriptors: (U) *BIOMETRY, *FINGERPRINTS, QUANTITATIVE ANALYSIS, VERIFICATION, CANADA, DATA ACQUISITION, IDENTIFICATION SYSTEMS, MULTIMODE, MANUAL OPERATION, VOICE COMMUNICATIONS
Identifiers: (U) AQ F05-11-3436, FOREIGN REPORTS, IBG(INTERNATIONAL BIOMETRIC GROUP)
Abstract: (U) DRDC-Ottawa contracted International Biometric Group (IBG) to develop a biometric fusion application, utilizing three distinct fingerprint systems and one voice verification system. This application enables biometric data collection and sample matching as well as operator configuration of multi-system matching logic. The application provides sufficient data for DRDC to perform a range of quantitative analysis on the utility of biometric systems that use multiple systems within a given modality and multiple systems within multiple modalities. This document provides background information on the biometric technologies implemented within this demonstration application (fingerprint and voice verification). It describes various multimodal biometric concepts of operation for both verification and identification systems. It details the functionality accessible through the biometric fusions application. Lastly it provides an Operator manual for the application.
Thermal Face Recognition in an Operational Scenario
Personal Author(s): Socolinsky, Diego A, Selinger, Andrea
Report Date: Jan 2004
Descriptors: (U) *SCENARIOS, *INFRARED IMAGES, *IDENTIFICATION SYSTEMS, *INFRARED RADIATION, THERMAL PROPERTIES, VISIBLE SPECTRA, FACE(ANATOMY), RECOGNITION, IMAGES, CONTROL, STATISTICS
Identifiers: (U) *THERMAL FACE RECOGNITION, *VISIBLE IMAGERY, THERMAL INFRARED IMAGERY
Abstract: (U) We present results on the latest advances in thermal infrared face recognition, and its use in combination with visible imagery. Previous research has shown high performance under very controlled conditions, or questionable performance under a wider range of conditions. This paper shows results on the use of thermal infrared and visible imagery for face recognition in operational scenarios. In particular, we show performance statistics for outdoor face recognition and recognition across multiple sessions. Our results support the conclusion that face recognition performance with thermal infrared imagery is stable over multiple sessions, and that fusion of modalities increases performance. As measured by the number of images and number of subjects, this is the largest ever reported study on thermal face recognition.
An Argument for the Use of Biometrics to Prevent Terrorist Access to the United States
Personal Author(s): Graham, Ray A
Report Date: 06 Dec 2003
Descriptors: (U) *TERRORISM, *BIOMETRY, TERRORISTS, POLICIES, UNITED STATES GOVERNMENT, THREATS, CHIPS(ELECTRONICS), IDENTIFICATION SYSTEMS
Abstract: (U) This paper considers measures that should be taken by the United States government to implement policies for a standardized personal identification system that includes the use of chip technology and biometrics to positively identify the bearer. The paper considers and expands upon the following discussion points: -Terrorism has changed significantly in recent years requiring different tactics techniques and procedures to meet this asymmetric threat. -Terrorist groups have expanded globally and groups operate around the world without regard to borders or national boundaries. This has made it more difficult to track and apprehend terrorists. -There has been an increase in the practice of identity theft by terrorist organizations as a technique to infiltrate agents and operatives into the United States. - Biometric technology offers a significantly improved method for positively identifying travelers entering the United States. The paper recommends the following: - -That the United States adopt a standard for a biometric identification card which is required for international travel. Include iris scanning and smart card technology to make use of embedded chip data storage encryption and biometrics to positively identify the bearer. -That automation architects develop a single shared international database of terrorist suspects violent dissidents and criminals which is accessible by world-wide agencies.
Testimony: Statement of Shelton Young, Director, Readiness and Logistics Support Directorate, Office of the Inspector General, Department of Defense, before the Subcommittee on National Security, Emerging Threats and International Relations, House Committee on Government Reform on "Emerging Threats: Assessing DoD Controls of Critical Chemical and Biological Equipment and Material
Report Date: 07 Oct 2003
Descriptors: (U) *BIOLOGICAL AGENTS, *THREATS, *RESEARCH FACILITIES, *DEFICIENCIES, *AREA SECURITY, *MICROORGANISMS, MANAGEMENT PLANNING AND CONTROL, EXPORTS, TRAINING, HUMANS, INVENTORY CONTROL, AGRICULTURE, HOUSE OF REPRESENTATIVES, PANEL(COMMITTEE), BACTERIAL TOXINS, IMPORTS, LIVESTOCK, ENTRY CONTROL SYSTEMS, RISK ANALYSIS, BIOMETRIC SECURITY
Identifiers: (U) *SECURITY CONTROLS, *PHYSICAL SECURITY, PERSONNEL ACCESS CONTROLS, CDC REGISTRATION, SECURITY TRAINING
Abstract: (U) This testimony presents the results of an Interagency Summary Report on Security Controls Over Biological Agents. The August 27, 2003, report consolidates issues identified in 27 reports published by the Offices of the Inspectors General of the Departments of Agriculture, Army, Defense, Energy, Health and Human Services, and Veterans Affairs. The summary report identified nine systemic problems: physical security, personnel access controls, inventory accountability and controls, contingency plans, registration with the Centers for Disease Control and Prevention (CDC), import and export of agents, safety and security training, management oversight, and policies and procedures. Deficiencies in security controls have serious implications for the health of United States' citizens, should those controls be breached and biological agents removed from the facility. Subsequent misuse of the biological agents could have serious health consequences and disrupt the country's agriculture, commerce, economy, and industry. Biological agents are micro-organisms, or their toxins, that cause or may cause human, animal, or plant diseases. Such disease-causing biological agents are termed pathogens. Select agents are pathogenic biological agents specifically described as having the potential to pose a severe threat to public or agricultural health and safety. For instance, anthrax (Bacillus anthracis), smallpox (Variola major), and the Ebola viruses are considered select agents by the CDC, while foot-and-mouth disease virus and classical swine fever virus are considered select agents by the Department of Agriculture. The CDC has identified 36 biological agents as select agents due to their potentially devastating effect on human populations. Correspondingly, the Department of Agriculture has identified an additional 33 biological agents as posing a threat to U.S. agricultural livestock or crop commodities.
Learning to Identify TV News Monologues by Style and Context
Personal Author(s): Snoek, Cees G, Hauptmann, Alexander G
Report Date: Oct 2003
Descriptors: (U) *AUTOMATION, *DETECTION, *PATTERN RECOGNITION, *MULTIMODE, *DIGITAL RECORDING SYSTEMS, *FEATURE EXTRACTION, *VIDEO RECORDING, PROBABILITY, SEMANTICS, MACHINE AIDED INDEXING, STATISTICAL ANALYSIS, RANKING, ARTIFICIAL INTELLIGENCE, LEARNING MACHINES, TELEVISION SYSTEMS, CASE STUDIES, CLASSIFICATION
Identifiers: (U) *TELEVISION BROADCASTING, *NEWS BROADCASTING, TV BROADCASTING, CONTENT ANALYSIS, AUTOMATIC INDEXING, VIDEO INDEXING, *VIDEO RETRIEVAL, DIGITAL VIDEOS, MULTIMODAL ANALYSIS, STATISTICAL CLASSIFICATION, MULTIMODAL PEOPLE DETECTION, FACE RECOGNITION, SEMANTIC LEARNING, CLASSIFIER ENSEMBLES, BROADCAST NEWS VIDEO, NEWS SUBJECT MONOLOGUES, STYLE DETECTORS, CONTEXT DETECTORS, FACIAL FEATURES, SPEAKER FEATURES, SPEECH TRANSCRIPT FEATURES, TRECVID BENCHMARK
Abstract: (U) This research focused on the problem of learning semantics from multimedia data associated with broadcast video documents. The authors proposed to learn semantic concepts from multimodal sources based on style and context detectors, in combination with statistical classifier ensembles. As a case study, they present their method for detecting the concept of news subject monologues. This approach had the best average precision performance amongst 26 submissions in the 2003 video track of the Text Retrieval Conference benchmark. Experiments were conducted with respect to individual detector contribution, ensemble size, and ranking mechanism. It was found that the combination of detectors is decisive for the final result, although some detectors might appear useless in isolation. Moreover, by using a probabilistic ranking in combination with a large classifier ensemble, the results can be improved even further.
Defense Healthcare Information Assurance Program (DHIAP) Phase III
Personal Author(s): Andrews, Archie
Report Date: Oct 2003
Descriptors: (U) *HEALTH CARE MANAGEMENT, *INFORMATION SECURITY, *INFORMATION ASSURANCE, TEST AND EVALUATION, DATA BASES, METHODOLOGY, AUTOMATION, ENVIRONMENTS, RISK, TOOLS, MEDICINE, ILLNESS, WORK STATIONS, CENTRALIZED
Identifiers: (U) OCTAVE, BIOMETRIC AUTHENTICATION, HIPAA PRIVACY, HIPA, JCAHO, DITSCAP, NIST BET PRACTICES, NIST SP-800-30, MISRT TRAINING
Abstract: (U) This report covers activities and accomplishments of Phase Ill of the Defense Healthcare Information Assurance Program% (DHIAP) for the period 30 July 2001 to 30 July 2003. Phase Ill tasks include: Technical Management, Deploy OCTAVE, OCTAVE Tools, OCTAVE Comparative Analysis, and Biometric Authentication Prototype. The Deploy OCTAVE effort developed and delivered DoD-specific training in use of the OCTAVE Methodology for conducting risk assessments. OCTAVE Tools developed two forms of automated support for the DoD's use of OCTAVE-a PC-based OCTAVE Automated Tool (OAT) to guide site Medical Information Security Response Teams (MlSRTs) through execution of OCTAVE while capturing data and generating interim and final reports, and a Risk Database (RDB) for centralized capture and analysis of site-level OAT data. OCTAVE Comparative Analysis produced reports comparing the OCTAVE process and outputs to other MHS requirements, specifically to execution and results of DlTSCAP, requirements of the HlPAA Security/Privacy Standards, JCAHO requirements, and requirements of the NIST Best Practices for Information Security (NIST SP 800-30). The Biometric Authentication Prototype effort developed and piloted a server and workstation outfitted with biometric authentication technologies (fingerprint, face, iris, and voice) and reported on utility/desirability of various biometric authentication approaches in medical environments with diverse characteristics.
The Science and Technology of Combating Terrorism
Personal Author(s): Augustine, Norman R, Arntzen, Charles J, Behrens, M K, Clough, G W, Gomory, Ralph, Healy, Bernadin, Kilberg, Bobbie, Nwabueze, E K, Papermaster, Steven G
Report Date: Jul 2003
Descriptors: (U) *PREPARATION, *MOBILIZATION, *PROTECTION, *COUNTERTERRORISM, *COOPERATION, *HOMELAND SECURITY, *TERRORISM, *PUBLIC HEALTH, NUCLEAR WEAPONS, ADVISORY ACTIVITIES, FIRST RESPONDERS, BIOMETRIC SECURITY, PANEL(COMMITTEE), COUNTERMEASURES, OPERATIONAL READINESS, PRESIDENT(UNITED STATES), STANDARDS, THREAT EVALUATION, STRATEGY, CORPORATIONS
Identifiers: (U) *SCIENCE AND TECHNOLOGY, RECOMMENDATIONS, BIODEFENSE, FOOD SECURITY, WATER SECURITY, DISASTER PREPAREDNESS, CITIZEN PREPAREDNESS, NATIONAL READINESS STRATEGY, NUCLEAR WEAPONS DETECTION, PRIVATE SECTOR, PUBLIC SECTOR, CYBERSECURITY
Abstract:(U) This report documents the work during 2002 and early 2003 of the President's Council of Advisors on Science and Technology (PCAST) Panel on the Science and Technology of Combating Terrorism. Because of the urgency of the nation's efforts to rally scientific, engineering, and technological resources in the war on terrorism, the findings of the Panel have, in large part, already been shared with the appropriate individuals in government throughout this time period, and many of the recommendations are currently being implemented in one form or another. The Panel's recommendations focus on protecting citizen health through the creation of a comprehensive national readiness strategy, helping first responders, helping businesses protect the nation, and improving the technology of personal identification. Importantly, the actions proposed emphasize helping citizens help themselves. The panel members also offer suggestions on cyberterrorism and other matters involving threat detection, assessment, and response. In each instance they attempt to acknowledge the activities that already exist in the private sector (citizen and corporate), and to suggest the appropriate governmental tools that could be applied to achieve the desired objectives in the particular situation addressed. As already noted, in a number of instances the Panel's recommendations are intended to confirm, augment, or refocus efforts that are currently under way or under consideration. The Panel's primary recommendations focus on Protecting Citizen Health and Safety -- A National Readiness Strategy, Public Health Preparedness, Helping First Responders, Helping Business Protect the Nation, Identity Authentication, Cybersecurity, and Detecting Nuclear Weapons.
Continuous Biometric Authentication for Authorized Aircraft Personnel: A Proposed Design
Personal Author(s): Carrillo, Cassandra M
Report Date: Jun 2003
Descriptors: (U) *COCKPITS, *AVIATION PERSONNEL, *BIOMETRY, AIRCRAFT, SECURITY, THESES, SOLUTIONS(GENERAL), INFLIGHT, PERSONNEL, INTRUSION, FLIGHT DECKS
Identifiers: (U) MULTIMODAL BIOMETRICS, BIMETRIC AUTHENTICATION SYSTEM, CONTINUOUS AUTHENTICATION, COMPUTER SECURITY FOR AIRCRAFT
Abstract: (U) Today, there is no way to ensure that the personnel working within the cockpit of an aircraft in flight are authorized to be there. The primary goal of this thesis is to propose a hypothetical design for the use of a non- intrusive mechanism on the flight deck of an aircraft to provide continuous or periodic authentication of authorized aircraft personnel. The mechanism should answer questions such as: "Is the person who is flying the plane actually the person who they say they are?" and "Is the correct person in control of the aircraft throughout the whole flight segment?" We will investigate biometrics as a possible security mechanism. In this thesis, various biometric methods are examined and their application in the flight deck is shown. Studies that have been conducted on real biometric devices are examined and their results are reported. Also examined are the current practices and procedures that take place in the flight deck, so that the proposed designs can be understood to not interfere with current activities therein. Two biometric solutions (i.e. proposed designs) to provide continuous or periodic authentication of authorized personnel in the flight deck are introduced. The proposed designs are general and can be used with different types of biometric device(s), and can be extended to include multi-biometrics.
Transforming Security Screening With Biometrics
Personal Author(s): Hearnsberger, Brian J
Report Date: 09 Apr 2003
Descriptors: (U) *MILITARY FACILITIES, *NATIONAL SECURITY, *COMPUTER APPLICATIONS, *BIOMETRY, *IDENTIFICATION, TERRORISTS, HANDS, FACE(ANATOMY), FINGERPRINTS, IRIS, SCANNERS, SCREENS(DISPLAYS), SAUDI ARABIA, SPEECH RECOGNITION, SOLUTIONS(GENERAL), GEOMETRY, ACCESS
Abstract: (U) How would you feel about having your face scanned and compared against your military identification card when entering a base? How about submitting your fingerprint before entering an airport security area and boarding a plane? Facial scans and fingerprinting are just two examples of biometrics, "the automated use of physiological or behavioral characteristics to determine or verify identity," that can reduce fraud and identity theft to dramatically improve physical security. Today, biometric technology could be implemented to transform physical security by enhancing screening procedures currently in use at U.S. bases worldwide and government-operated screening points throughout America.
The Wireless Ubiquitous Surveillance Testbed
Personal Author(s): Ford, Michael K, Dennis, LeRoy P , III
Report Date: Mar 2003
Descriptors: (U) *TEST BEDS, *SURVEILLANCE, *BIOMETRY, DETECTORS, STRATEGY, THESES, HYPOTHESES, HABITATS, MATURATION, TECHNOLOGY ASSESSMENT
Identifiers: (U) UBIQUITOUS SURVEILLANCE, FACIAL RECOGNITION
Abstract: (U) The thesis research examines the emergence of surveillance and biometrics technologies as a sensible baseline for building a ubiquitous surveillance testbed for the Naval Postgraduate School, This thesis also defines what ubiquitous surveillance is, employs biometric applications and technical strategies to build a working testbed, and addresses developmental issues surrounding the hypothesis for a ubiquitous surveillance testbed. The authors conduct several evaluations of the testbed in using different scenarios, We recommend emerging biometric and surveillance technologies can promote the maturation of the testbed into a premier ubiquitous habitat,
Biometrics Technology Review 2002
Personal Author(s): Blackburn, T, Butavicius, M. Graves, I, Hemming, D, Ivancevic, V
Report Date: Mar 2003
Descriptors: (U) *PATTERN RECOGNITION, *AREA SECURITY, *BIOMETRY, *BIOMETRIC SECURITY, OPTICAL DETECTION, VALIDATION, DEOXYRIBONUCLEIC ACIDS, COSTS, RELIABILITY, INFRARED IMAGES, USER NEEDS, SPEECH RECOGNITION, RETINA, BIOLOGICAL DETECTION, AUSTRALIA, MATCHING, OPTICAL SCANNING, ACCEPTABILITY, VEINS, EAR, HANDS, WORD RECOGNITION, FACE(ANATOMY), FINGERPRINT RECOGNITION, COMPUTER ACCESS CONTROL, INFORMATION SECURITY, DATA TRANSMISSION SECURITY, INTRUSION DETECTION(COMPUTERS)
Identifiers: (U) *ACCESS CONTROL, SIGNATURE MATCHING, IRIS SCANNING, AQ F03-10-2288, FOREIGN REPORTS
Abstract: (U) The September 11, 2001 terrorist attacks in the United States have motivated renewed global efforts to secure national borders. Accordingly, Australian authorities have demonstrated an interest in mechanisms that support these endeavors. This report examines the state of current biometric research, covering the literature up to October 2002. The report characterizes the main categories of biometric techniques, with a focus on face recognition, which is the least intrusive but most effective means of applying filters at access points to the country. It describes the basic technologies inherent in the four major taxonomies used in identification methodologies. These comprise authentication and validation approaches, each based on one-to-one and one-of-many models. The report provides descriptions of the following biometric categories, including discussions of their strengths and weaknesses: fingerprint technologies that employ a number of different sensors (i.e., capacitive, optical, imaging infrared, ultrasonic, mechanical, hygiene) that produce two-dimensional maps of fingerprints; face recognition technologies in which maps of the face are analyzed, processed, stored, and used in the matching process; hand dimension, palm pattern, and vein pattern matching; iris and retina scanning; voice analysis; signature matching; keystroke filtering; DNA matching; ear shape matching; and work patterns, such as typing speed and choice of words in a document. Some applications of these biometric techniques include access controls to physical locations and computer systems and identification procedures in medical, military, and government domains. A table shows how each of the techniques studied compare with one another in terms of access control, surveillance, accuracy, reliability, error rate, false positives/negatives, security, stability, user acceptance, intrusiveness, ease of use, cost, strengths, and weaknesses. (1 table, 4 figures, 176 refs.)
Relative Contributions of Internal and External Features to Face Recognition
Personal Author(s): Jarudi, Izzat N, Sinha, Pawan
Report Date: Mar 2003
Descriptors: (U) *RESOLUTION, *RECOGNITION, *FACE(ANATOMY), INTERNAL, VISION, EYE, EXTERNAL, IMAGES
Identifiers: (U) *FACIAL FEATURES
Abstract: (U) The central challenge in face recognition lies in understanding the role different facial features play in our judgments of identity. Notable in this regard are the relative contributions of the internal (eyes, nose and mouth) and external (hair and jaw-line) features. Past studies that have investigated this issue have typically used high-resolution images or good-quality line drawings as facial stimuli. The results obtained are therefore most relevant for understanding the identification of faces at close range. However, given that real-world viewing conditions are rarely optimal, it is also important to know how image degradations, such as loss of resolution caused by large viewing distances, influence our ability to use internal and external features. Here, we report experiments designed to address this issue. Our data characterize how the relative contributions of internal and external features change as a function of image resolution. While we replicated results of previous studies that have shown internal features of familiar faces to be more useful for recognition than external features at high resolution, we found that the two feature sets reverse in importance as resolution decreases. These results suggest that the visual system uses a highly non-linear cue-fusion strategy in combining internal and external features along the dimension of image resolution and that the configural cues that relate the two feature sets play an important role in judgments of facial identity.
Ability of the Vericator to Detect Smugglers at a Mock Security Checkpoint
Personal Author(s): Brown, Troy E, Senter, Stuart , Ryan, Andrew H , Jr
Report Date: 24 Feb 2003
Descriptors: (U) *STRESS(PSYCHOLOGY), *SPEECH ANALYSIS, *VOICE COMMUNICATIONS, STRESS ANALYSIS, IDENTIFICATION SYSTEMS, SPEECH RECOGNITION, LAW ENFORCEMENT, SMUGGLING, LIE DETECTORS
Identifiers: (U) VERICATOR
Abstract: (U) This study assessed the ability of Vericator(TM), a computer-based system that evaluates credibility through speech, to detect smugglers at a mock security checkpoint. A U.S. Federal inspector questioned participants while Vericator assessed their credibility. For some (N=77), the inspector followed a script of questions without follow-up (Scripted); for the remainder (N=93), follow-up questions were permitted (Field-like). Smuggling base rates were 34% and 35%, respectively. Few smugglers were correctly identified at the checkpoint (3 of 26 and 6 of 33, respectively) while many non-smugglers were correctly identified (41 of 51 and 47 of 60, respectively). Subsequent analyses produced widely disparate results but indicate that future improvements may be possible. However, the use of Vericator at security checkpoints is not supported at this time.
Biometrics: A Look at Facial Recognition
Personal Author(s): Woodward, John D , Jr, Horn, Christopher, Gatune, Julius, Thomas, Aryn
Report Date: Jan 2003
Descriptors: (U) *BIOMETRY, *FACE(ANATOMY), VIRGINIA, POLICIES, RECOGNITION, ASSEMBLY, LEGISLATION, LAW ENFORCEMENT, POLICE, PUBLIC SAFETY, CRIMES
Identifiers: (U) FACIAL RECOGNITION
Abstract: (U) During the 2002 General Assembly, Delegate H. Morgan Griffith sponsored legislation that would set legal parameters for public sector use of facial recognition technology in Virginia. The legislation, known as House Bill No. 454 (included as an Appendix), passed the House of Delegates by a vote of 74-25 earlier this year, and is pending in the Senate Courts of Justice Committee while the Virginia State Crime Commission examines it. The Virginia State Crime Commission, a standing legislative commission of the Virginia General Assembly, is statutorily mandated to make recommendations on all areas of public safety in the Commonwealth of Virginia. Currently, Virginia Beach is the only municipality in Virginia planning to incorporate facial recognition technology into its public safety efforts. Late last year, the Virginia Beach City Council approved a measure authorizing the installation of a facial recognition system in the city's "Oceanfront" tourist area. The system has been tested and has recently been fully implemented. Senator Kenneth W. Stolle, the Chairman of the Virginia State Crime Commission, established a Facial Recognition Technology Sub-Committee to examine the issue of facial recognition technology. This briefing begins by defining biometrics and discussing examples of the technology. It then explains how biometrics may be used for authentication and surveillance purposes. Facial recognition is examined in depth to include technical, operational, and testing considerations. This briefing concludes with a discussion of the legal status quo with respect to public sector use of facial recognition. While not making a specific policy recommendation with respect to House Bill No. 454, this briefing hopefully provides useful information for Sub-Committee members, the Virginia State Crime Commission, and other interested parties.
Towards Pervasive Robotics
Personal Author(s): Arsenio, Artur M
Report Date: Jan 2003
Descriptors: (U) *IMAGE PROCESSING, *PORTABLE EQUIPMENT, *ROBOTS, *MOBILE, *HEAD(ANATOMY), *BIONICS, ROBOTICS, SOCIAL COMMUNICATION, THREE DIMENSIONAL, SEARCHING, PATTERN RECOGNITION, AUTONOMOUS NAVIGATION, NIGHT VISION, AREA SECURITY, TARGET DETECTION, ATTENTION, THERMAL IMAGES, COLOR VISION, EYE MOVEMENTS
Identifiers: (U) *ROBOTIC HEADS, MACACO ROBOT, MOBILE PLATFORMS, OBJECT ANALYSIS, SOFTWARE ARCHITECTURE
Abstract: (U) In the near future, pervasive robotics will require small, light, and cheap robots that exhibit complex behaviors. These demands led to the development of the M2-M4 Macaco project -- a robotic active vision head. Macaco is a portable system, capable of emulating the head of different creatures both aesthetically and functionally. It integrates mechanisms for social interactions, autonomous navigation, and object analysis.
Person Identification from Video with Multiple Biometric Cues: Benchmarks for Human and Machine Performance
Personal Author(s): O'Toole, Alice J
Report Date: Jan 2003
Descriptors: (U) *PERFORMANCE(HUMAN), *BIOMETRY, *PHOTOGRAPHIC IMAGES, DATA BASES, PERFORMANCE(ENGINEERING), PICTURES, FACE(ANATOMY)
Identifiers: (U) *FACE RECOGNITION, FACIAL MOTION, GAIT, VIDEO DATABASE
Abstract: (U) We have compiled a database of images and videos that includes images and videos of approximately 300 human participants. Duplicate sets of images and videos taken from 1 week to 6 months after the first set are available for approximately 200 of these people. The images include 9 standard "mug shot poses". The videos include head rotations, dynamic facial expressions, facial speech clips, and 3 whole-body gait clips. Experiments have been completed comparing the effects of several types of facial motion on face recognition, the effects of face familiarity on recognition from video clips taken at a distance, and on the effects of attention on recognition of moving faces. The results of these studies provide insight into the way motion can facilitate or interfere with the encoding of the invariant face and body features that support recognition.
Evaluation and Improvement of a Speaker Verification System in Military Environments
Personal Author(s): Heide, David A
Report Date: 26 Dec 2002
Descriptors: (U) *CODING, *SPEECH RECOGNITION, *VOICE COMMUNICATIONS, *BIOMETRIC SECURITY, ALGORITHMS, VERIFICATION, MILITARY APPLICATIONS, NAVAL RESEARCH
Identifiers: (U) PE33904N, PE61153N
Abstract: (U) The U.S. Navy is constantly looking for ways to improve security. One of the possible solutions proposed has been the use of biometrics, defined by the Biometric Consortium as "automated methods of recognizing a person base on a physiological or behavioral characteristic". One of the least costly, most convenient, and least invasive methods of biometrics is speaker verification. The Naval Research Laboratory's Voice Systems Section has undergone an extensive study of a commercial speaker verification system in adverse military noise and voice encoding environments. Additional testing was conducted to study the amount of improvement that could be achieved using a noise canceling preprocessor. This report documents the performance results in 10 different military noise environments, six different voice encoding algorithms, and all combinations of the two, with and without noise cancellation. Results show that speaker verification definitely show promise under some conditions. In many cases, a significant improvement in performance was achieved by using a noise cancellation preprocessor. While more testing needs to be done to gauge the level of performance under live conditions, this report shows system integrators where speaker verification could possibly be used.
Voice Biometrics for Information Assurance Applications
Personal Author(s): Kang, George , Lee, Yvette
Report Date: 05 Dec 2002
Descriptors: (U) *SPEECH RECOGNITION, *VOICE COMMUNICATIONS, *BIOMETRY, INFORMATION SYSTEMS, VERIFICATION, MILITARY APPLICATIONS, SPEECH ANALYSIS, MESSAGE PROCESSING, CONFIDENCE LEVEL
Identifiers: (U) VOICE BIOMETRICS, PE61553N
Abstract: (U) In 2002, the President of the United States established an organization within the DOD to develop and promulgate biometrics technologies to achieve security in information, information systems, weapons, and facilities. NRL has been tasked to study voice biometrics for applications in which other biometrics techniques are difficult to apply. The ultimate goal of voice biometrics is to enable the use of voice as a password. Voice biometrics are "man-in-the-loop" systems in which system performance is significantly dependent on human performance. This aspect has not been properly emphasized by previous researchers in this field. Accordingly, we let each speaker choose his (or her) own test phrase that can be uttered consistently. The speech waveform is then pre-processed (i.e, equalized and normalized) to reduce the effect of inconsistent speaking. Subsequently, we extract five different voice features from the speech waveform. Some of them have never been used for voice biometrics. Finally, individual feature errors are combined to indicate a confidence level of speaker verification. Initial laboratory testing under various conditions shows encouraging results. We will be prepared to fleet-test our voice biometrics system in FY03.
Face Recognition Using Infrared Imaging
Personal Author(s): Pereira, Diogo C
Report Date: Dec 2002
Descriptors: (U) *INFRARED IMAGES, *COMPUTER APPLICATIONS, *RECOGNITION, *FACE(ANATOMY), DATA BASES, AUTOMATION, IMAGES, CLASSIFICATION, SPEECH RECOGNITION, DISCRIMINATION, COLLECTION, CONTROLLED ATMOSPHERES
Abstract: (U) This study investigated a (IR) face recognition system using an uncooled IR camera. A computer-based image collection set-up was designed and used to create a small database of 420 facial images, from 14 volunteers. Manual and automated facial image cropping routines were implemented. Two linear approaches (PCA and LDA) for the dataset dimension reduction and classification were implemented and their resulting classification performances compared. Results show that the best PCA-based average classification performance is equal to 92,22% while the LDA-based classification performance is equal to 99,40%. These results successfully show that an uncooled IR camera may be used to disseminate between individual subjects obtained from a small database collected under a very controlled environment.
Gesture Recognition System for Hand and Arm Signals
Personal Author(s): Lampton, Donald R, Knerr, Bruce W, Clark, Bryan R, Martin, Glenn A, Washburn, Donald A
Report Date: Nov 2002
Descriptors: (U) *COMPUTER APPLICATIONS, *PATTERN RECOGNITION, *VIRTUAL REALITY, *HANDS, *ARMS(ANATOMY), SOFTWARE ENGINEERING, OPTICAL TRACKING, VISUAL SIGNALS
Identifiers: (U) *HAND SIGNALS, *ARM SIGNALS, *GESTURES, *GESTURE RECOGNITION
Abstract: (U) This report describes an evaluation of a computer system for recognizing human hand and arm signals as a means of interacting with virtual environments. The system consists of two video cameras, software to track the positions of the gesturer's head and hands. and software to recognize gestures by analyzing the position and movement of the hands. The software was hosted on a standard PC. A set of 14 gestures from Army Field Manual 2l-6O. Visual Signals. was used to test the system. Ten participants individually performed each gesture twice as discrete trials. with a brief rest period between each trial. The average recognition rate was 68%. The highest average recognition rate for an individual was 86%; the lowest was 57%. Three of the 14 gestures were always recognized correctly. and one was never recognized correctly. While no tracking failures occurred for four ofthe gestures, tracking failures ranged from 10% to 100% for the other ten. The system's capabilities for untagged optical tracking and recognition of gestures involving certain types of repetitive motion advance the state-ofthe-art in computer-based gesture recognition. However. for training applications. substantial improvements are needed in tracking reliability and recognition of gestures involving the depth dimension.
A Surveillance Society and the Conflict State: Leveraging Ubiquitous Surveillance and Biometrics Technology to Improve Homeland Security
Personal Author(s): Makarski, Ricahrd E, Marreno, Jose A,
Report Date: Sep 2002
Descriptors: (U) *SURVEILLANCE, *TERRORISM, *HOMELAND SECURITY, WARFARE, GLOBAL, DETECTION, SOCIETIES, MONITORING, NETWORKS, THESES, CATALYSTS, CONFLICT, HYPOTHESES, CIVIL AFFAIRS, BIOMETRY, CRIMINOLOGY
Abstract: (U) The thesis research examines the emergence of surveillance and biometrics technologies as a pragmatic baseline supporting the goals of homeland security. Assessment of existing catalysts of the world condition, conflict states, terrorist and criminal networks have facilitated increased U.S. and international attention to the field of surveillance and biomertic technology. This study scrutinizes surveillance, biomertic techniques, strategies, and prevailing present day applications. It contrasts the evolving requirements for improved security with a balanced consideration of civil liberties and privacy. The authors address developmental issues surrounding the hypothesis for a ubiquitous surveillance grid to monitor and combat terrorism, crime, and other contributing illicit behaviors. The authors recommend that federal, state, local, and corporate agencies unite in improving homeland security by implementing the deterrence, detection, monitoring, and response actions that these technologies have to offer.
DRDC Toronto/HPP Metabolic Measurement Software V2.0. Users' Manual
Personal Author(s):Keefe, Allan A
Report Date: Aug 2002
Descriptors: (U) *COMPUTER PROGRAMS, *METABOLISM, *BIOMETRY, *SOFTWARE TOOLS, USER MANUALS, DATA PROCESSING, INPUT, MEASUREMENT, CANADA, FAILURE, ACCURACY, GRAPHICS, LOSSES, DATA DISPLAYS
Identifiers: (U) FOREIGN REPORTS
Abstract: (U) As a result of changes in computer technology, an update to the DRDC Toronto/HPP Metabolic Measurement Software was deemed necessary. In addition to making this software compliant with the WindowsTM 32-bit operating system, several enhancements were made to improve its usability and accuracy of measurements. These include; a wizard' to facilitate test set-up data entry, protection of data loss due to equipment failure, compensation for system lag, graphical display of data, and integration with Microsoft ExcelTM for data exporting, saving and analysis. This document is a manual to assist the operator in the usage of this software.
Positive Identity Verification System and Method Including Biometric User Authentication
Personal Author(s): Houvener, Robert C
Report Date: 23 Jul 2002
Descriptors: (U) *PATENTS, *BIOMETRIC SECURITY, DATA BASES, IDENTIFICATION SYSTEMS, AREA SECURITY, REMOTE AREAS, THERMAL IMAGES, BIOMETRY, AUDITING, FINGERPRINTS, VOICEPRINTS
Identifiers: (U) IATAC COLLECTION, PAT-CL-340-5.82, *POSITIVE IDENTIFICATION SYSTEM, RETINAL SCANS, *USER AUTHENTICATION
Abstract: (U) A system and method of providing system integrity and audit capabilities to a positive identification system is disclosed. In the preferred embodiment, the system uses biomimetic access authority information units and a biomimetic comparison system at a remote database site to permit authorized system users to access the positive identification system. The system also utilizes secondary access authority information units to permit authorized system users to access the system in the event that one or more authorized system users cannot be authenticated using the biomimetic comparison system.
Methods and Apparatus for Correlating Biometric Attributes and Biometric Attribute Production Features
Personal Author(s): Herman-Maes, Stephane, Zweig, Geoffrey G
Report Date: 25 Jun 2002
Descriptors: (U) *BIOMETRY, *PATENTS, MATHEMATICAL MODELS, PROBABILITY DISTRIBUTION FUNCTIONS, STATISTICS, CORRELATION, IDENTIFICATION SYSTEMS, SPEECH RECOGNITION, COMPUTER PROGRAM VERIFICATION, INVENTIONS, BIOMETRIC SECURITY
Identifiers: (U) *BIOMETRIC ATTRIBUTES, PAT-CL-704-273, IATAC COLLECTION
Abstract: (U) A method of validating production of a biometric attribute allegedly associated with a user comprises the following steps. A first signal is generated representing data associated with the biometric attribute allegedly received in association with the user. A second signal is also generated representing data associated with at least one feature detected in association with the production of the biometric attribute allegedly received from the user. Then, the first signal and the second signal are compared to determine a correlation level between the biometric attribute and the production feature, wherein the validation of the production of the biometric attribute depends on the correlation level. Accordingly, the invention serves to provide substantial assurance that the biometric attribute offered by the user has been physically generated by the user.
Training on the Web: Identifying and Authenticating Learners
Personal Author(s): Curnow, Christina K , Freeman, Michael W, Wisher, Robert A, Belanich, James
Report Date: Jun 2002
Descriptors: (U) *TRAINING, *ARMY PERSONNEL, *INTERNET, EDUCATION, DATA PROCESSING SECURITY, ASYNCHRONOUS SYSTEMS, PERFORMANCE TESTS, INSTRUCTIONS, ONLINE SYSTEMS, LEARNING, WORKSHOPS, BIOMETRY
Identifiers: (U) PE665803
Abstract: (U) Soldiers who receive training in the workplace, at their residences, or at other sites outside the traditional classroom increasingly rely upon asynchronous distributed learning systems. This accentuates the need to identify various forms of training compromise, such as obtaining questions beforehand or enlisting a proxy for test taking in non-proctored, web-based learning environments. A one-day workshop, summarized in this report, was conducted to identify practical solutions to training compromise on the Web or military intranets. Experts from government, academia, and industry generated solutions in the areas of test security, biometrics (including fingerprint identification, face recognition, iris scanning, and hand writing recognition), legal issues, public key infrastructure, instructional design, and test design. Following the workshop, an Army advisory group prioritized the solutions into a final list of recommendations, included here as a starting point for addressing and preventing training compromise.
Tokenless Biometric Electronic Transactions Using an Audio Signature to Identify the Transaction Processor
Personal Author(s): Hoffman, Ned, Pare, David Ferrin, Jr, Lee, Jonathan Alexander, Lapsley, Phillip Dean
Report Date: 28 May 2002
Descriptors: (U) *DATA BASES, *IDENTIFICATION SYSTEMS, *ELECTRONIC SECURITY, *BIOMETRY, *PATENTS, USER NEEDS, SIGNATURES, COMPUTER APPLICATIONS, TRANSDUCERS, SOUND GENERATORS
Identifiers: (U) *ELECTRONIC TRANSACTIONS, BIOMETRIC SAMPLES, AUDIO SIGNATURES, TOKENLESS BIOMETRIC IDENTIFICATION SYSTEM, PAT-CL-705-44, IATAC COLLECTION
Abstract: (U) The invention discloses a tokenless biometric identification computer system, comprising at least a database containing registered biometric samples of users. A comparator compares a bid biometric sample of a user to at least one registered biometric sample, the bid biometric sample obtained directly from the user during an identification process for conducting an electronic transaction by the user. A stored audio signature is associated with a transaction processor entity, which the transaction processor entity is responsible for conducting the electronic transaction. A sound generator generates an analog or digital signal from the stored audio signature, and a transducer converts the analog or digital signal to a play back audio signature. This invention generates a play back audio signature from the stored audio signature that is associated with the transaction processor entity and the play back audio signature is played back to the user to identify the transaction processor entity that conducted the electronic transaction, wherein no man made personal devices such as credit cards, identity cards or the like is used during the identification process for conducting the electronic transaction.
Secure Wireless Communication User Identification By Voice Recognition
Personal Author(s): Ulvinen, Vesa, Paloniemi, Jari
Report Date: 21 May 2002
Descriptors: (U) *COMMUNICATIONS NETWORKS, *SPEECH RECOGNITION, *VOICE COMMUNICATIONS, *RADIOTELEPHONES, STATIONS, DATA TRANSMISSION SYSTEMS, NETWORKS, MOBILE, IMAGES, GRAPHICS, RESOURCES, WORDS(LANGUAGE), RADIO LINKS, TRANSDUCERS, STORAGE, TELEPHONE SYSTEMS, PATENTS
Identifiers: (U) IATAC COLLECTION, PAT-CL-455-563
Abstract:(U) A method to authorize or authenticate a user of a wireless telecommunication system (32), and includes steps of (a) selecting a word at random from a set of reference words, or synthesizing a reference word; (b) prompting the user to speak the reference word; and (c) authenticating the user to operate in, or through, or with a resource reachable through the wireless telecommunication system, only if the users speech characteristics match pre-stored characteristics associated with the reference word. In one embodiment the steps of selecting or synthesizing, prompting, and authenticating are performed in a mobile station (10) having a speech transducer (19) for inputting the user's speech, while in another embodiment at least one of the steps of selecting or synthesizing, prompting, and authenticating are performed in a wireless telecommunications network (32) that is coupled between the mobile station and a telephone network (35). In yet another embodiment at least one of these steps are performed in a data communications network resource (38) that is coupled through a data communications network (37), such as the Internet, and the wireless telecommunications network to the mobile station. The step of prompting may include a step of displaying alphanumeric text and/or a graphical image to the user using a display (20) of the mobile station.
Biometric Authorization and Registration Systems and Methods
Personal Author(s): Caulfield, H J, Halter, Ernest
Report Date: 28 Apr 2002
Descriptors: (U) *BIOMETRY, ALGORITHMS, PATENT APPLICATIONS, SMALL ARMS, COMPUTER APPLICATIONS
Identifiers:(U) *AUTHORIZED USERS, AUTHORIZATION, REGISTRATION, IATAC COLLECTION, UNAUTHORIZED USERS
Abstract: (U) Biometric authorization and registration systems and methods are disclosed. In one embodiment, the system preferably comprises a firearm that includes a biometric authorization system, a plurality of training computers, and a server. In the preferred embodiment, the server and the training computer interact to train the biometric authorization system in the firearm to accurately and reliably discriminate between the authorized user and unauthorized users. The server utilizes a training algorithm that takes into account biometric information of not only the authorized user of firearm, but also those of a large number of unauthorized users. Such biometric information is utilized to compute one or more discriminants and thresholds for such discriminant(s), which are then transmitted to the biometric authorization system in the firearm. If the user is allowed to operate the firearm a predetermined percentage of the time, the discriminant thresholds are fixed. If not, the server adjusts the thresholds, and the process is repeated. In another aspect of the present invention, the system may be utilized to uniquely register the firearm with the authorized user. Similar training algorithms are also disclosed for training biometric authorization systems in devices other than firearms.
NATIONAL PREPAREDNESS: Technologies to Secure Federal Buildings
Report Date: 25 Apr 2002
Descriptors: (U) *NATIONAL SECURITY, *UNITED STATES GOVERNMENT, *NATIONAL DEFENSE, DETECTION, FACILITIES, ATTACK, VULNERABILITY, BUILDINGS, REPORTS, LONG RANGE(TIME), INTERNATIONAL TRADE, TERRORISM, HEARING, BIOMETRY, HINGES, RISK MANAGEMENT
Abstract: (U) Thank you for inviting me to participate in today s hearing on security technologies to protect federal facilities. The terrorist attacks of September 11 on the World Trade Center and the Pentagon have intensified concerns about the physical security of our federal buildings and the need to protect those who work in and visit these facilities. These concerns have been underscored by reports of long-standing vulnerabilities, including weak controls over building access. As you requested, today I will discuss commercially available security technologies that can be deployed to protect these facilities, ranging from turnstiles, to smart cards, to biometric systems. While many of these technologies can provide highly effective technical controls, the overall security of a federal building will hinge on establishing robust risk management processes and implementing the three integral concepts of a holistic security process: protection, detection, and reaction.
United States Homeland Security and National Biometric Identification
Personal Author(s):Janker, Peter S
Report Date: 09 Apr 2002
Descriptors: (U) *IDENTIFICATION SYSTEMS, *TERRORISM, *HOMELAND SECURITY, TERRORISTS, DEPARTMENT OF DEFENSE, UNITED STATES, ENVIRONMENTS, ORGANIZATIONS, MANAGEMENT, VERIFICATION, THREATS, REACTIVITIES, POPULATION, SAFETY, TEMPLATES, BIOMETRY
Abstract: (U) The threat of terrorism is real. The acts of Sept 11th demonstrated that our enemy is resourceful and able to operate with ease within our homeland and among our population. The consequences of continuing to provide terrorists with the ability to operate within the United States with impunity is to welcome additional and likely more devastating attacks. The United States is currently operating in a reactive mode and must become proactive if we are to prevent further unnecessary loss of innocent lives. Our willingness to prepare for further terrorist operations by implementing appropriate biometric identification/verification systems within the United States will determine the impact and success of future terrorist acts. Our challenge is to establish a national identification system that not only provides protection against our enemies but protects the values and respect for privacy that makes up the fabric that comprises American. In order to accomplish this we must be able to determine if our current methods of verifying identity are capable of handling the threat of terrorism. If not what steps should the Executive Branch and the Department of Defense (DoD) take to address the shortfalls? This study will attempt to answer these questions through the use of ends, ways and means analysis template to address the development of a national identification system and by identifying the role that the Department of Defense and its Biometric Management Office should play in the emerging Homeland Defense organization. The current focus of the military, in regards to biometrics, is on itself not on American society. We can accomplish both our mission of implementing biometrics within DoD and enjoying the safe secure environment we create. Today we are ignoring DoD's role in implementing a national identification system based on biometrics.
A Comparative Analysis of Face Recognition Performance With Visible and Thermal Infrared Imagery
Personal Author(s): Socolinsky, Diego A, Selinger, Andrea
Report Date: Jan 2002
Descriptors: (U) *INFRARED IMAGES, *RECOGNITION, *THERMAL IMAGES, *FACE(ANATOMY), ALGORITHMS, METHODOLOGY
Abstract: (U) We present a comprehensive performance analysis of multiple appearance-based face recognition methodologies, on visible and thermal infrared imagery. We compare algorithms within and between modalities in terms of recognition performance, false alarm rates and requirements to achieve specified performance levels. The effect of illumination conditions on recognition performance is emphasized, as it underlines the relative advantage of radiometrically calibrated thermal imagery for face recognition.
Component-Based Face Detection
Personal Author(s): Heisele, Bernd, Serre, Thomas, Pontil, Massimiliano, Poggio, Tomaso
Report Date: Dec 2001
Descriptors: (U) *PATTERN RECOGNITION, *COMPUTER VISION, *FACE(ANATOMY), SYMPOSIA, FEATURE EXTRACTION, LEARNING, DETECTION
Identifiers: (U) *FACE DETECTION, *SVM(SUPPORT VECTOR MACHINES), *CLASSIFIERS, COMPONENTS, MACHINE LEARNING
Abstract: (U) We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support Vector Machine (SVM) classifiers. On the first level, component classifiers independently detect components of a face. On the second level, a single classifier checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face. We propose a method for automatically learning components by using 3-D head models. This approach has the advantage that no manual interaction is required for choosing and extracting components. Experiments show that the component-based system is significantly more robust against rotations in depth than a comparable system trained on whole face patterns.
Department of Defense Physical Security Equipment Guide
Personal Author(s): Elkins, Eric, Farrar, Mike,
Report Date: Dec 2001
Descriptors: (U) *CONTROL SYSTEMS, *SECURITY, USER MANUALS, MILITARY FACILITIES, ESPIONAGE, DAMAGE, SAFETY, PROTECTION, ACCESS, INTRUSION DETECTORS, SECURITY PERSONNEL, CARDS, BIOMETRY, WARNING SYSTEMS, THEFT, METAL DETECTORS, EXPLOSIVES DETECTION
Identifiers: (U) *PHYSICAL SECURITY EQUIPMENT
Abstract: (U) This user's guide serves as a reference document on physical security equipment for security personnel. It is not comprehensive, but serves as an overview and guide for security personnel to properly select and use security equipment.
Investigation and Evaluation of Voice Stress Analysis Technology
Personal Author(s): Haddad, Darren, Walter, Sharon, Ratley, Roy, Smith, Megan
Report Date: Nov 2001
Descriptors: (U) *STRESS ANALYSIS, *STRESS(PSYCHOLOGY), *SPEECH ANALYSIS, *VOICE COMMUNICATIONS, COMPUTER PROGRAMS, MILITARY PERSONNEL, IDENTIFICATION SYSTEMS, SPEECH RECOGNITION, DECEPTION, LAW ENFORCEMENT
Identifiers: (U) WUAFRLNURSA13
Abstract: (U) Numerous police officers and agencies have been approached in recent years by vendors touting computer-based systems capable of measuring stress in a person's voice as an indicator of deception. These systems are advertised as being cheaper, easier to use, less invasive in use, and less constrained in their operation than polygraph technology. They claim that a speaker's medical condition, age, or consumption of drugs does not affect use of their system. Voice stress analysis does not require physical attachment of the system to the speaker's body and does not require that answers be restricted to 'yes' and 'no'. Purportedly, according to some vendors, any spoken word or even a groan, whether recorded, videotaped, or spoken in person, with or without the speaker's knowledge, are acceptable inputs to voice stress analysis systems. The value of voice stress analysis technology' for military application could be extensive. During military field interrogations of potential informants, it could be applied in a manner similar to its application for law enforcement. Also, it's not known if stressed speech has any effects on the accuracy of speech technology, such as speaker identification and language identification. If voice stress can be detected, perhaps it can be taken into account in applying voice recognition technology and be used to improve these recognition capabilities. Therefore, this effort is to determine the scientific value and utility of existing, commercial voice stress analysis technology for law enforcement and military applications.
Simulation of Optical Skin Lesion Images
Personal Author(s): She, Zhishun, Fish, P J, Duller, A W
Report Date: 25 Oct 2001
Descriptors: (U) *OPTICAL IMAGES, *LESIONS, IMAGE PROCESSING, SIMULATION, OPTICAL PROPERTIES, COLORS, PATTERN RECOGNITION, TEXTURE, SKIN(ANATOMY), UNITED KINGDOM
Identifiers: (U) FOREIGN REPORTS, SKIN LESION
Abstract: (U) Black-white and colour skin/lesion images are synthesised with known characteristics such as boundary, skin pattern and colour. The skin and lesion textures are modelled by the auto-regressive (AR) process. Black-white skin lesion images are obtained by combining black-white skin and lesion textures under control of known lesion shape and colour skin lesion images are generated by mixing the coloured skin and lesion textures, Artefact images of skin hair and specular reflection are then added. The synthesised images provide the image set for evaluating image processing algorithms.
Monocameral Visual Recognition of Marcus Hand Postures for Personal Robotic Assistants
Personal Author(s): Gonzalo-Tasis, M, Laschi, C, Finat, J, Dario, P
Report Date: 25 Oct 2001
Descriptors: (U) *ROBOTICS, *VISUAL PERCEPTION, *HANDS, *POSTURE(PHYSIOLOGY), SIMULATION, DETECTORS, HUMANS, TRACKING, IDENTIFICATION, CONFIGURATIONS, MOBILE, PATTERN RECOGNITION, VISION, SYMBOLS, SPAIN, JOINTS(ANATOMY), BIOMECHANICS, PERCEPTION, TOUCH, PROSTHETICS, FINGERS
Identifiers: (U) FOREIGN REPORTS
Abstract: (U) The postures recognition is the first step for the gestures tracking of an artificial or a natural hand. In this article, we show a visuo-motor tracking of mobile hand configurations, which is based on symbolic representations able of supporting the biomechanical and perceptual information relative to evolving postures. After recognition, we have a virtual skeleton to identify simulated artificial hands. Such postures identification is adapted to an artificial Marcus hand developed as a human prosthesis. Nevertheless, the complex mechatronic device, this symbolic representation allows the visual identification and tracking of hand points of interest, such as tactile sensors and finger joints. In this way, a feedback for the perception-action cycle is obtained to improve the man- machine interaction in Personal Robotics, with special regard to the assistance of disabled people.
A Simulation and Experimental Study on Equivalent Dipole Layer Imaging of Brain Electric Sources
Personal Author(s): Lian, J , Yao, D , Wu, D , He, B
Report Date: 25 Oct 2001
Descriptors: (U) *BRAIN, *ELECTRIC POWER, *PATTERN RECOGNITION, *VISION, *LASER HAZARDS, *LASER DAMAGE, *ELECTROENCEPHALOGRAPHY, SIMULATION, SOURCES, SPATIAL DISTRIBUTION, FORWARD AREAS, HUMANS, LAYERS, RESOLUTION, FAR FIELD, CONFIGURATIONS, REVERSIBLE, IMAGES, DIPOLES, LEVEL(QUANTITY), PATTERNS, MAPS, NOISE, STIMULI, HEAD(ANATOMY), PERCEPTION, SKIN(ANATOMY), VISUAL SIGNALS
Identifiers: (U) VEP(VISUAL EVOKED POTENTIALS), EDLI(EQUIVALENT DIPOLE LAYER IMAGING)
Abstract: (U) A simulation and experimental study has been conducted on equivalent dipole layer imaging (EDLI) of brain electric sources from EEC, Using the three-sphere inhomogeneous head model, the performance of the EDLI was rigorously evaluated for a variety of brain source configurations under different noise levels, The present simulation results demonstrate the excellent performance of the EDLI in mapping and imaging the underlying cortical sources with much enhanced spatial resolution, as compared to the scalp potentials, Human experiments were further conducted to examine the feasibility of EDLI Pattern reversal visual evoked potentials (VEP) were recorded from 94 electrodes and the brain electric sources at PlOO were estimated, The VEP experiments demonstrate that the present EDLI can eliminate the misleading far field in the scalp potential map, localize and map the underlying cortical sources induced by the visual stimuli.
Text-Independent Speaker Identification by Genetic Clustering Radial Basis Function Neural Network
Personal Author(s): Yue, Xicai, Ye, Datian, Liu, Ming
Report Date: 25 Oct 2001
Descriptors: (U) *SPEECH RECOGNITION, SYMPOSIA, NEURAL NETS, CLUSTERING, CHINA
Identifiers: (U) FOREIGN REPORTS
Abstract: (U) The authors combine genetic clustering algorithm with radial basis function neural network (RBFNN) for avoiding locally optimum solutions in speaker identification. The effectiveness of genetic clustering algorithm is evaluated with speech utterances by comparing with normal clustering method. Speaker identification experiments show that generic clustering RBFNN can improve the correctness of text-independent speaker identification.
Muscular Biometry With Magnetic Resonance Imaging
Personal Author(s): Zoabli, G, Mathieu, P A, Malanda, A
Report Date: 25 Oct 2001
Descriptors: (U) *MUSCLES, *BIOMETRY, CANADA, DIAGNOSIS(MEDICINE), ELECTRODES, SPAIN, ORTHOGONALITY, SUBCUTANEOUS TISSUE, FAT CELLS, MAGNETIC RESONANCE IMAGING
Identifiers: (U) FOREIGN REPORTS
Abstract: (U) Electromyographic (EMG) signal obtained from surface electrodes is frequently used to evaluate muscular activity. Analysis of this signal can be facilitated if anatomy of the implicated muscles is known as well as thickness of subcutaneous fat layer and of the skin under the electrodes. Such information can be obtained with a manual segmentation procedure applied on magnetic resonance images (MRI) obtained in three orthogonal planes.
The Relationship Between Arm Movement and Walking Stability in Bipedal Walking
Personal Author(s): Shibukawa, Miki, Sugitani, Kazuhiko, Hong, Renshan, Kasamatsu, Keiko
Suzuki, Satoshi, Ninomija, Satoki P
Report Date: 25 Oct 2001
Descriptors: (U) *WALKING, *PHYSIOLOGICAL EFFECTS, *BIOMETRY, *ARMS(ANATOMY), KINEMATICS, STABILITY, SYMPOSIA, ANALYSIS OF VARIANCE, JAPAN, KINETICS, SHOULDERS(ANATOMY), POSTURE(PHYSIOLOGY), TREADMILLS
Identifiers: (U) *ARM MOVEMENT, *WALKING MOVEMENT, *WALKING STABILITY, *SHOULDER FULCRUM DISPERSION, *BIPEDAL WALKING, WALKING SPEED, *ARM LEG INTERACTIONS, FOREIGN REPORTS
Abstract: (U) Research on bipedal walking is currently underway in a variety of fields. In engineering, robots that can walk in a bipedal manner are now under development, and, in medicine, important data on human walking characteristics are being gathered for use in the clinical analysis of walking for use in rehabilitation programs. The analysis of walking movement has generally focused on the legs rather than the arms, probably due to a perception that the arms do not play an essential role in this movement. However, if a quantitative understanding of arm movement functions can be obtained, this data will prove invaluable in the fields of robotics, sports physiology, and rehabilitation research. This study focuses on the relationship between arm movement and walking stability during bipedal walking. Subjects were 8 healthy, young males without walking disabilities who mounted an electric treadmill and walked in three different modes: unrestrained, with arms strapped to the sides of the body, and with arms swung up 90 degrees. In each of these modes the treadmill was set to 3 speeds. Subjects walked for 2 minutes at each speed in each mode (9 different mode-speed combinations). Movement was videotaped from two different positions. Analysis of variance was conducted for each measurement item using the factors of walking posture and speed. Results showed that at high walking speed (5.7 km/hr), the Shoulder Fulcrum Dispersion (SFD) was significantly higher for walking with arms immobilized than for unrestrained walking. This indicates that, at low and medium speeds (2.7 km/hr and 4.2 km/hr, respectively), the effect of restricted arm movements on upper body posture was minimal, whereas, at high speed, its effect on stability was considerable. The use of SFD as an index in this study provided a comparison with the subjective evaluations of the subjects as well as a quantitative understanding of walking stability based on analysis of variance. (5 figures, 4 references)
Comparative Analysys of Speech Parameters for the Design of Speaker Verification Systems
Personal Author(s): Souza, A F, Souza, M N
Report Date: 25 Oct 2001
Descriptors: (U) *SPEECH RECOGNITION, *BIOMETRY, BRAZIL, FEATURE EXTRACTION
Identifiers: (U) FOREIGN REPORTS
Abstract: (U) Speaker verification systems are basically composed of three stages: feature extraction, feature processing and comparison of the modified features from speaker voice and from the voice that should be verified. Many features have been used in the first stage, although the current literature has not already shown the best of them. Based on the biometrics hypothesis, which states that each individual has a physical characteristic that distinguishes itself from the others, this paper realized a comparison between 12 classical widely used parameters, in order to investigate the biometrics hypothesis. The obtained results point out those parameters directly correlated to speaker's anatomy which are among the best ones that can be used in the development of speaker verification systems.
Biometrics: Facing Up to Terrorism
Personal Author(s): Woodard, John D , Jr
Report Date:Oct 2001
Descriptors: (U) *IDENTIFICATION SYSTEMS, *COUNTERTERRORISM, *BIOMETRY, TERRORISTS, PUBLIC SAFETY, THEFT, FACE(ANATOMY), HANDWRITING, FINGERPRINT RECOGNITION, VOICEPRINTS
Identifiers: (U) *BIOMETRICS, IATAC COLLECTION, VOICE RECOGNITION, FACE RECOGNITION, IDENTITY THEFT
Abstract: (U) Biometrics refer to the use of a person's physical characteristics or personal traits to identify, or verify the claimed identity of that individual. Finger prints, faces, voices, and handwritten signatures are all examples of characteristics that have been used to identify a person. This issue paper discusses how biometric technologies could be used to impede terrorism in three critical areas: (1) Controlling access to sensitive facilities at airports; (2) Preventing identity theft and fraud in the use of travel documents; and (3) Identifying known or suspected terrorists. It further offers a proposed counterterrorist application that uses a type of biometric known as facial recognition to identify terrorists.
Adaptive Control of Distributed Agents Through Pheromone Techniques and Interactive Visualization
Personal Author(s): Parunak, H V, Posdamer, Jeff , Sauter, John A , Brueckner, Sven
Report Date: Oct 2001
Descriptors: (U) *COMPUTER PROGRAMS, *ROBOTICS, *ARTIFICIAL INTELLIGENCE, BIOMETRY, PHEROMONES
Identifiers: (U) FINE-GRAINED AGENTS, AIR CAMPAIGN CONTROL, STIGMERGY, PE63760E, WUAFRLJ1160001
Abstract: (U) Software agents guided by synthetic pheromones can imitate the stigmergetic dynamics of insects. The resulting software architecture is well suited to problems such as the control of air campaigns and unmanned robotic vehicles. An architecture for the deployment of synthetic pheromones in a military setting is described. The architecture can be instantiated into a single computer, a distributed network of computers, or even across a mass network of field processors implanted in the environment. Software agents representing the military units of interest move through this synthetic environment sensing and depositing synthetic pheromones. These agents are able to locate and select targets dynamically. Using ant colony optimization techniques, the agents build safe paths to the target that adapt in real time to new threats or opportunities. The results produced can be used to help guide manned missions, or to directly control unmanned robotic vehicles. The technology has particular advantages for controlling large swarms of small, unmanned vehicles.
Implications of User Identification Devices (UIDS) for the United States Navy
Personal Author(s): Haynes, Letitia D,
Report Date: Sep 2001
Descriptors: (U) *IDENTIFICATION SYSTEMS, *ETHICS, *MICROSENSORS, NAVAL PERSONNEL, THESES, MILITARY MEDICINE, RADIOFREQUENCY, BIOMETRY, IMPLANTATION
Identifiers: (U) UID(USER IDENTIFICATION DEVICES), MICROCHIPS
Abstract: (U) Various technologies are emerging to provide enhanced, automated personnel identification capabilities. Techniques for human microchip implants using radio frequency identification are possible, but the implications of this technology remain to be considered. This thesis provides a survey of current technologies for enhanced user identification, focusing on human implant approaches, and to summarize the set of security, privacy, social and ethical issues that may arise from the use of these technologies in the U.S. Navy. Technical background is presented to provide the reader with a basic understanding of radio frequency technology. An analysis of human implant technologies currently used in the private sector is provided to show how they might offer capabilities in the military. Applications of information technology and human microchip implants that may improve user identification in the future are presented and analyzed. Finally, a review of the social and ethical implications of human implant-based user identification is provided. It shows that the collateral social issues are complex and far-reaching, and need to be carefully considered by the Navy to avoid becoming entangled in intractable technical, morale and legal issues far into the future. The results of this exploratory thesis show: 1) implementation of advanced information technology devices must be carefully balanced against human social and ethical considerations, and 2) there is a valid need for future research and analysis of human microchip implants.
Advanced Data Analysis Methods for Analyte Recognition from Optical Sensor Arrays
Final rept. 1 Apr 1999-31 Mar 2001
Personal Author(s): Priebe, Carey E
Report Date: 30 Jun 2001
Descriptors: (U) *STATISTICS, *PATTERN RECOGNITION, *NOSE(ANATOMY), DATA PROCESSING, ADAPTIVE SYSTEMS, ARTIFICIAL INTELLIGENCE, SMELL, HYPERSPECTRAL IMAGERY
Identifiers: (U) ARTIFICIAL NOSES
Abstract: (U) The objectives of this project were, simply put, to develop advanced statistical pattern recognition methodologies for the Tufts University artificial nose (and other sensors of interest -- notably, hyperspectral imagers). This effort had significant positive impact on the Tufts University artificial nose. In particular, I claim that the paper: C.E. Priebe, 'Olfactory Classification via Interpoint Distance Analysis', IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. No. 4, pp. 404-413, April 2001, is among the most important papers ever published on statistical pattern recognition for artificial olfactory sensor systems. Additional publications detail advancements made which positively impact the Tufts nose (and are applicable to many other sensor systems). Furthermore, this effort produced workable initial versions of a methodology for jointly optimizing classification with sensing and processing, in terms of adaptive dimensionality reduction. This latter concept is relevant to a wide variety of adaptive sensors, and will be pursued in the future.
Correlation System for Security Validation and Verification Using An Encoded Phase Mask
Personal Author(s): Weber, David C, Trolinger, James D
Report Date: 26 Jun 2001
Descriptors:(U) *ELECTROOPTICS, *HOLOGRAPHY, *IDENTIFICATION SYSTEMS, DATA BASES, AUTOMATION, DATA MANAGEMENT, CRYPTOGRAPHY, VERIFICATION, VALIDATION, SECURITY, INTENSITY, SENSITIVITY, CORRELATION, BIOMETRY, HOLOGRAMS, SCANNERS, REPRODUCTION(COPYING), PHOTOCHROMIC MATERIALS
Identifiers: (U) BIOMETRICS, FINGERPRINT IDENTIFICATION, HOLOGRAPHIC SEAL, PHASE MASK, SECURITY VERIFICATION, ENCRYPTION, BACTERIORHODOPSIN, SBIR(SMALL BUSINESS INNOVATION RESEARCH), JTC(JOINT TRANSFORM CORRELATOR)
Abstract: (U) Verification technologies are needed to confirm the identity of personnel and to validate the authenticity of manufactured products. Rapid advances in computers, printers scanners, and copiers have made it increasingly easy to reproduce security emblems traditionally used for verification and authentication. Even holograms, once considered impenetrable, are now routinely counterfeited using techniques such as holographic contact copying. To circumvent the effectiveness of intensity sensitive devices to copy traditional security emblems, the use of complex phase patterns has been proposed. An ID card is produced by bonding a phase mask to some primary identification pattern such as a fingerprint. A nonlinear joint transform correlator is then used to match the ID card to an identical phase mask that is part of an automated reader. However, such a phase encoded ID card could be copied by using innovative holographic techniques. To avoid this, MetroLaser has developed an innovative holographic technique that utilizes an ID card that is an inseparable combination of an information wavefront and another complex wavefront, both unknown to the potential counterfeiter. The two patterns on the card are deconvolved using a 'Key' Hologram that is part of the reader, resulting in a nearly ideal security system.
Building Standardized 3D Face Data Base for Face Recognition Applications
Personal Author(s): Vetter, Thomas, Blanz, Volker
Report Date: May 2001
Descriptors: (U) *DATA BASES, *PATTERN RECOGNITION, *FACE(ANATOMY), IMAGE PROCESSING, ILLUMINATION, THREE DIMENSIONAL, UNITED KINGDOM
Identifiers: (U) *FACE RECOGNITION, FOREIGN REPORTS, AQ F02-06-1081, MORPHABLE MODELS
Abstract: (U) During the past 9 months we concentrated our work on three main issues: First, we developed of methods and software for processing three-dimensional face data and started a collaboration with the University of Florida to obtain and process a large set of high quality laser scans of human heads that might be valuable for future research on automated face recognition. Second, we derived a morphable face model from a selected subset of the face data collected so far using a method we developed earlier. Third, we now also performed a series of first experiments on using a three-dimensional morphable face model for pose and illumination invariant face recognition. The results of these experiments demonstrated that the morphable model is a promising approach for compensating pose variations up to 90 deg.
Super Bowl Surveillance: Facing Up to Biometrics
Personal Author(s): Woodward, John D , Jr
Report Date: May 2001
Descriptors:(U) *RECOGNITION, *BIOMETRY, LAW ENFORCEMENT, COUNTERMEASURES, INTRUSION, FACE(ANATOMY)
Identifiers: (U) FACIAL RECOGNITION, PRIVACY RIGHTS
Abstract: (U) Biometric facial recognition can provide significant benefits to society. At the same time, the rapid growth and improvement in the technology could threaten individual privacy rights. The concern with balancing the privacy of the citizen against the government interest occurs with almost all law enforcement techniques, however, and we should not let the fear of potential but inchoate threats to privacy, such as super surveillance, deter us from using facial recognition where it can produce positive benefits. Biometric facial recognition is by no means a perfect technology, and much technical work has to be done before it becomes a truly viable tool to counter terrorism and crime. But the technology is getting better and there is no denying its tremendous potential. In the meantime, we, as a society, have time to decide how we want to use this new technology. By implementing reasonable safeguards, we can harness Its power to maximize its benefits while minimizing the intrusion on individual privacy.
Information Security: Securing Smart Cards With IRIS Recognition
Personal Author(s): Phelps, Orval E
Report Date: Mar 2001
Descriptors:(U) *RECOGNITION, *IRIS, *INFORMATION SECURITY, REQUIREMENTS, SKILLS, CRYPTOGRAPHY, BIOLOGY, LITERATURE SURVEYS, PHYSICAL PROPERTIES, PROCESSING, THESES, TIME, CODING, RELIABILITY, STRENGTH(GENERAL), ACCESS, STORAGE, LIFE SPAN(BIOLOGY), CARDS, HIGH RELIABILITY
Abstract: (U) This thesis examines the application of iris recognition technology to the problem of keeping smart cards secure. In order to understand the technology, a comprehensive literature review was conducted. The biological components of the iris were examined to ensure that they were truly random in development and static through the lifetime of the individual. Specifically, the physical structure of what comprises the iris was examined in detail. The data gathered indicates that the iris is formed early in development, random in structure, and stable throughout the person's lifetime. Next, the iris recognition process and resulting recognition code was examined to determine how it could be used. Examination of methods to eliminate counterfeit codes and the randomness of independent codes was vital. Statistics on reliability of the iris recognition process were also examined. Iris recognition was found to be exceptionally reliable, difficult to counterfeit and fast to use. In order to ensure security, the cryptographic strength of the iris recognition code was examined. It was necessary to determine the time necessary to break the iris recognition code should the smart card be compromised, Due to the randomness of the code, exhaustive searches are the only viable means of breaking the code and the time durations to accomplish this are excessive. Additionally, smart card technology was examined to determine if existing technology could store the necessary iris recognition information for use in identity verification. Current processing ability and storage requirements of smart cards exceed the minimum requirements for use of iris recognition technology. The conclusion of this thesis is that iris recognition technology is a viable means of securing smart cards against unauthorized access with high reliability, confidence and speed.
Face Recognition Vendor Test 2000: Evaluation Report
Personal Author(s): Blackburn, Duane M, Bone, Mike , Phillips, P J
Report Date: 16 Feb 2001
Descriptors: (U) *RECOGNITION, *FACE(ANATOMY), *TECHNOLOGY ASSESSMENT, TEST AND EVALUATION, REQUIREMENTS, COMMERCE, MARKETING, PERFORMANCE(ENGINEERING), COSTS, VENDORS
Identifiers: (U) FERET(FACE RECOGNITION TECHNOLOGY)
Abstract: (U) The biggest change in the facial recognition community since the completion of the FERET program has been the introduction of facial recognition products to the commercial market. Open market competitiveness has driven numerous technological advances in automated face recognition since the FERET program and significantly lowered system costs. Today there are dozens of facial recognition systems available that have the potential to meet performance requirements for numerous applications. But which of these systems best meet the performance requirements for given applications? Repeated inquiries from numerous government agencies on the current state of facial recognition technology prompted the DoD Counterdrug Technology Development Program Office to establish a new set of evaluations. The Facial Recognition Vendor Test 2000 (FRVT 2000) was cosponsored by the DoD Counterdrug Technology Development Program Office, the National Institute of Justice and the Defense Advanced Research Projects Agency and was administered in May and June 2000.
Face Recognition Vendor Test 2000: Appendices
Descriptors: (U) *IDENTIFICATION, *BIOMETRY, TEST AND EVALUATION, DATA BASES, COMMERCE, MARKETING, VERIFICATION, PERFORMANCE TESTS, TEST METHODS, IMAGES, PROCUREMENT, RECOGNITION, VENDORS, FACE(ANATOMY)
Abstract: (U) The DoD Counterdrug Technology Development Program Office, the National Institute of Justice (NlJ), the Defense Advanced Research Projects Agency (DARPA), NAVSEA Crane Division and NAVSEA Dahlgren Division are sponsoring an evaluation of commercial off the shelf (COTS) facial recognition products. The purpose of these evaluations is to accurately gauge the capabilities of facial recognition biometric systems that are currently available for purchase. The sponsoring agencies, as well as other government agencies, will use this information as a major factor when determining future procurement or development efforts. Participation in these tests is open to all facial recognition systems on the US commercial market. The U.S. Government will not compensate vendors to participate in these tests. Two categories of tests will be conducted: Recognition Performance Tests and Product Usability Tests For each category, multiple tests will be performed to measure system performance in verification mode and in identification mode. The Recognition Performance Tests will use the FERET test methodology with a new database of images. The Product Usability Tests will evaluate performance in both low and medium security access control scenados.
CBEFF Common Biometric Exchange File Format
Personal Author(s): Podio, Fernando L, Dunn, Jeffrey S, Reinert, Lawrence, Tilton, Catherine J, O'Gorman, Lawrence
Report Date: 03 Jan 2001
Descriptors: (U) *BIOMETRY, COMPUTER PROGRAMS, DATA MANAGEMENT, INFORMATION EXCHANGE, INTEROPERABILITY, COMPATIBILITY, FORMATS, CONSORTIUMS, WORKSHOPS
Identifiers: (U) IATAC COLLECTION, *CBEFF(COMMON BIOMETRIC EXCHANGE FILE FORMAT), DATA ELEMENTS, SMART CARDS
Abstract: (U) The Common Biometric Exchange File Format (CBEFF) describes a set of data elements necessary to support biometric technologies in a common way. These data can be placed in a single file used to exchange biometric information between different system components or between system. The result promotes interoperability of biometric-based application programs and systems developed by different vendors by allowing biometric data interchange. CBEFF's initial conceptual definition was achieved through a series of three Workshops co-sponsored by the National Institute of Standards and Technology and the Biometric Consortium. A Technical Development Team, formed as a result of these Workshops, developed CBEFF, as described in this publication, in coordination with industrial organizations (i.e., the BioAPI Consortium, the X9.F4 Working Group, the International Biometric Industry Association, and the Interfaces Group of TeleTrusT) and end users. CBEFF provides forward compatibility accommodating for technology improvements and allows for new formats to be created. CBEFF implementations simplify integration of software and hardware provided by different vendors. Further development (e.g., a CBEFF smart card format) is proposed under the umbrella of the recently formed Biometrics Interoperability, Performance, and Assurance Working Group co-sponsored by MST and the Biometric Consortium.
Face Recognition with Support Vector Machines: Global versus Component-Based Approach
Personal Author(s): Heisele, Bernd, Ho, Purdy, Poggio, Tomaso
Report Date: Jan 2001
Descriptors:(U) *PATTERN RECOGNITION, *FACE(ANATOMY), DATA BASES, FEATURE EXTRACTION, MAN MACHINE SYSTEMS, VECTOR ANALYSIS
Identifiers: (U) SVM(SUPPORT VECTOR MACHINE)
Abstract: (U) We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first locate facial components, extract them and combine them into a single feature vector which is classified by a Support Vector Machine (SVM). The two global systems recognize faces by classifying a single feature vector consisting of the gray values of the whole face image. In the first global system we trained a single SVM classifier for each person in the database. The second system consists of sets of viewpoint-specific SVM classifiers and involves clustering during training. We performed extensive tests on a database which included faces rotated up to about 40 deg in depth. The component system clearly outperformed both global systems on all tests.
RAND Arroyo Center Research Brief: Can Biometrics Help the Army Solve An Identity Crisis?
Report Date: Jan 2001
Descriptors: (U) *MILITARY REQUIREMENTS, *INFORMATION SYSTEMS, *RESEARCH FACILITIES, *BIOMETRY, DATA BASES, WEAPONS, PEACETIME, COMMUNITIES, PHYSICAL PROPERTIES, DATA STORAGE SYSTEMS, ARMY
Abstract: (U) The Army is having an identity crisis, and it affects both its wartime and peacetime operations. Simply put, the Army needs to ensure that the right people and only the right people can get access to its information systems, its weapons, and its many databases that serve the Army community. Biometrics-that is, physical characteristics or personal traits that can be measured quickly may offer a solution. But using biometrics raises some knotty legal, ethical, and sociological issues-for example, how to safeguard biometric information so it cannot be used for other, possibly nefarious, purposes. The Army has been studying these issues and has been considering the feasibility of establishing a biometric research center that could serve as a central data repository and carry out test and evaluation.
Applying Practical Formal Methods to the Specifications and Analysis of Security Properties
Personal Author(s): Heitmeyer, Constance
Report Date: Jan 2001
Descriptors: (U) *COMPUTER PROGRAMS, *SOFTWARE TOOLS, REQUIREMENTS, SPECIFICATIONS, COST REDUCTION, SECURITY, ERRORS, BIOMETRY
Abstract: (U) The SCR (Software Cost Reduction) toolset contains tools for specifying, debugging, and verifying system and software requirements. The utility of the SCR tools in detecting specification errors, many involving safety properties, has been demonstrated recently in projects involving practical systems, such as the International Space Station, a flight guidance system, and a U.S. weapons system. This paper briefly describes our experience in applying the tools in the development of two secure systems: a communications device and a biometrics standard for user authentication.
Army Biometric Applications. Identifying and Addressing Sociocultural Concerns
Personal Author(s): Woodward, John D , Jr, Webb, Katharine W , Newton, Elaine M , Bradley, Melissa
Report Date: Jan 2001
Descriptors:(U) *DATA PROCESSING SECURITY, *BIOMETRY, COMPUTER COMMUNICATIONS, OPERATIONAL EFFECTIVENESS, IDENTIFICATION SYSTEMS, ACCESS, COMPUTER NETWORKS, INFORMATION WARFARE
Identifiers: (U) ACCESS CONTROL, RAND REPORTS, BIOMETRICS
Abstract: (U) The U.S. Army has a growing need to control access to its systems in times of both war and peace. In wartime, the Army's dependence on information as a tactical and strategic asset requires the Army to carefully control its battlefield networks. From logistics flows to intelligence on enemy forces, the Army depends on confining access to its data to authorized personnel. This need for access control is also critical at the weapon system level. Access control issues are important to the peacetime Army because improving the efficiency of peacetime operations, including controlling access to facilities, computer systems, and classified information, depends on fast and accurate identification. The Army also operates a vast set of human resource services involving health care, retiree and dependent benefits, and troop support services. These services create the need for positive identification to prevent fraud and abuse.
Online and Unsupervised Face Recognition for Humanoid Robot: Toward Relationship with People
Personal Author(s): Aryananda, Lijin
Report Date: Jan 2001
Descriptors: (U) *ROBOTS, *SOCIAL PSYCHOLOGY, *HUMAN RELATIONS, INTERACTIONS, RECOGNITION, DOLPHINS(MAMMALS), BEHAVIOR, ANIMALS, OBSERVATION
Identifiers: (U) HUMANOID ROBOT
Abstract: (U) The ability to recognize and remember individuals is crucial and has important implications for the evolution of animal social behavior, particularly complex interactions within groups. Male dolphins have been found to form coalitions, where each group possesses a fertile female. Observation of behavior within the coalitions indicates complex social behavior where dolphins often form coalitions of coalitions , but each sub-coalition mates only with its own female. This implies the existence of complex social interaction, such as preferential treatment, cooperative behavior, and reciprocity . Such a relationship demands the ability to distinguish conspecific group members as individuals and as kin, remember their relative ranks and past affiliations, and in some cases, remembers the personal histories of help given and received from others .
Smaller, Smarter C4ISR: Presentation to Defense Science & Technology Seminar
Personal Author(s): Fernandez, F L
Report Date: 08 Dec 2000
Descriptors: (U) *MINIATURIZATION, *MICROELECTROMECHANICAL SYSTEMS, ROBOTICS, INFRARED DETECTORS, INERTIAL NAVIGATION, DRONES, OPTICAL DETECTORS, BIOMETRY, ACOUSTIC DETECTORS, MOLECULAR ELECTRONICS
Identifiers: (U) IATAC COLLECTION, C4ISR, JOINT VISION 2020
Abstract: (U) A DARPA presentation which discusses the needs for smaller and smarter C4ISR technologies.
An Approach to Feature-Based Face Recognition
Personal Author(s): Vrabel, Michael J
Report Date: Dec 2000
Descriptors: (U) *PATTERN RECOGNITION, IMAGE PROCESSING, SIZES(DIMENSIONS), TARGET RECOGNITION, SHAPE, PHOTOGRAPHIC IMAGES, FACE(ANATOMY), AUTOMATIC TRACKING
Identifiers: (U) SCENE ANALYSIS, ATR(AUTOMATIC TARGET RECOGNITION), AUTOMATIC TARGETING
Abstract: (U) I detail a scheme for searching an unknown scene for occurrences of an object. The approach is independent of object size, location, and orientation and is tolerant of significant changes in object shape and appearance.
SCoPE, Syllable Core and Periphery Evaluation: Automatic Syllabification and Application to Foreign Accent Identification
Personal Author(s): Berkling, Kay, Vonwiller, Julie, Cleirigh, Chris
Report Date: Aug 2000
Descriptors: (U) *SPEECH RECOGNITION, *FOREIGN LANGUAGES, *SYLLABLES, *PHONEMES, POSITION(LOCATION), SYMPOSIA, CORES, INVENTORY, ENGLISH LANGUAGE, MORPHEMES, VIETNAM, AUSTRALIA, MORPHOLOGY, BOUNDARIES, WORDS(LANGUAGE)
Identifiers: (U) COMPONENT REPORTS, NATO FURNISHED
Abstract: (U) In this paper we apply a study of the structure of the English language towards an automatic syllabification algorithm. Elements of syllable structure are defined according to both their position in the syllable and to the position of the syllable within word structure. Elements of syllable structure that only occur at morpheme boundaries or that extend for the duration of morphemes are identified as peripheral elements; those that can occur anywhere with regard to word morphology are identified as core elements. All languages potentially make a distinction be- tween core and peripheral elements of their syllable structure, however the specific forms these structures take will vary from language to language. In addition to problems posed by differences in phoneme inventories, we expect speakers with the greatest syllable structural differences between native and foreign language to have greatest difficulty with pronunciation in the foreign language. In this paper we will analyses two accents of Australian English: Arabic whose core/periphery structure is similar to English and Vietnamese, whose structure is maximally different to English.
Multilingual Text-Independent Speaker Identification
Personal Author(s): Durou, Geoffrey
Report Date: Aug 2000
Descriptors: (U) *SPEECH RECOGNITION, *LINGUISTICS, DATA BASES, SYMPOSIA, POPULATION, LANGUAGE
Identifiers: (U) *MULTILINGUAL SYSTEMS, COMPONENT REPORTS, FOREIGN REPORTS, NATO FURNISHED, NAN NATIVE LANGUAGE, TEXT INDEPENDENT SPEAKER
Abstract: (U) In this paper, we investigate two facets of speaker recognition : cross-language speaker identification and same language non-native text-independent speaker identification. In this context, experiments have been conducted, using standard multi-gaussian modeling, on the brand new multi-language TNO corpus. Our results indicate how speaker identification performance might be affected when speakers do not use the same language during the training and testing, or when the population is composed of non-native speakers.
Automatic Language Identification
Personal Author(s): Zissman, Marc A, Berkling, Kay M
Report Date: Aug 2000
Descriptors: (U) *SPEECH RECOGNITION, *ANALOG TO DIGITAL CONVERTERS, *NATURAL LANGUAGE, DATA BASES, SYMPOSIA, AUTOMATIC, IDENTIFICATION, HISTORY, LANGUAGE
Identifiers: (U) *SPEECH UTTERANCE, COMPONENT REPORTS NATO FURNISHED
Abstract: (U) Automatic language identification is the process by which the language of a digitized speech utterance is recognized by a computer. In this paper, we will describe the set of available cues for language identification and discuss the different approaches to building working systems. This overview includes a range of historic approaches, con- temporary systems that have been evaluated on standard databases, as well as promising future approaches. Com- parative results are also reported.
Vowel System Modeling: A Complement to Phonetic Modeling in Language Identification
Personal Author(s): Pellegrino, Francois, Farinas, Jerome, Andre-Obrechi, Regine
Report Date: Aug 2000
Descriptors: (U) *HUMAN FACTORS ENGINEERING, *SPEECH RECOGNITION, *MAN COMPUTER INTERFACE, *PHONETICS, ALGORITHMS, SYMPOSIA, VOWELS, AUTOMATIC, MALES, LANGUAGE, IDENTIFICATION, DETECTION
Identifiers: (U) COMPONENT REPORTS, FOREIGN REPORTS, NATO FURNISHED
Abstract: (U) Most systems of Automatic Language Identification are based on phonotactic approaches. However, it is more and more evident that taking other features (phonetic, phonological, prosodic, etc.) into account will improve performances. This paper presents an unsupervised phonetic approach that aims to consider phonological cues related to the structure of vocalic and consonantal systems. In this approach, unsupervised vowel/non vowel detection is used to model separately vocalic and consonantal systems. These Gaussian Mixture Models are initialized with a data-driven variant of the LBG algorithm: the LBG-Rissanen algorithm. With 5 languages from the OGI MLTS corpus and in a closed set identification task, the system reaches 85 % of correct identification using 45-second duration utterances for male speakers. Using the vowel system modeling as a complement to an unsupervised phonetic modeling increases this performance up to 91 % while still requiring no labeled data.
Is Biometrics an Age Verification Technology
Personal Author(s): Woodward, John D , Jr
Report Date: Jun 2000
Descriptors: (U) *VERIFICATION, *RECOGNITION, *ONLINE SYSTEMS, *BIOMETRY, SCANNING, CONGRESS, POLICIES, PHYSICAL PROPERTIES, SITES, PROTECTION, PHYSIOLOGY, LEARNING, CHILDREN
Abstract: (U) On June 9, 2000, John D. Woodward, Jr., a RAND Senior Policy Analyst, testified before a hearing of the Commission on Online Child Protection. Congress created the Commission in October 1998 to "identify technological or other methods that will help reduce access by minors to material that is harmful to minors on the Internet." The Commission invited Woodward to discuss biometrics, or methods of automatically recognizing a person using distinguishing physical characteristics and personal traits. Examples of biometrics include digitized fingerprints, retinal and iris scans, speaker recognition and hand geometry. Addressing the Commission's interest in learning if biometrics could determine someone's age, Woodward testified that "This Commission understandably wants to protect children from accessing online sites that are harmful to minors. As part of its effort, the Commission has correctly asked whether there are any kinds of commercially- viable age verification biometrics. The good news is there are many kinds of commercially-viable biometrics. The bad news is there are no age verification biometrics, no age determination biometrics and no age estimation biometrics.
Face Detection in Still Gray Images
Personal Author(s): Heisele, Bernd, poggio, Tomaso, Pontil, Massimilinao
Report Date: May 2000
Descriptors: (U) *DETECTION, *FACE(ANATOMY), IMAGES, VECTOR ANALYSIS, PATTERN RECOGNITION, MAN MACHINE SYSTEMS
Identifiers: (U) SVMS(SUPPORT VECTOR MACHINES), FACE DETECTION
Abstract: (U) We present a trainable system for detecting frontal and near-frontal views of faces in still gray images using Support Vector Machines (SVMs). We first consider the problem of detecting the whole face pattern by a single SVM classifier. In this context we compare different types of image features, present and evaluate a new method for reducing the number features and discuss practical issues concerning the parameterization of SVMs and the selection of training data. The second part of the paper describes a component-based method for face detection consisting of a two-level hierarchy of SVM classifiers. On the first level, component classifiers independently detect components of a face, such as the eyes, the nose, and the mouth. On the second level, a single classifier checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face.
Secure Continuous Biometric-Enhanced Authentication
Personal Author(s): Klosterman, Andrew J, Ganger, Gregory R
Report Date: May 2000
Descriptors: (U) *DATA PROCESSING SECURITY, SOFTWARE ENGINEERING, PERFORMANCE(ENGINEERING), EIGENVECTORS, OPERATING SYSTEMS(COMPUTERS), ELECTRONIC SECURITY, SECURE COMMUNICATIONS, BIOMETRY, NETWORK ARCHITECTURE
Identifiers: (U) COMPUTER SECURITY, AUTHENTICATION, BIOMETRIC, LINUX
Abstract: (U) Biometrics have the potential to solidify person authentication by examining "unforgeable" features of individuals. This paper explores issues involved with effective integration of biometric-enhanced authentication into computer systems and design options for addressing them. Because biometrics are not secrets, systems must not use them like passwords; otherwise, biometric-based authentication will reduce security rather than increase it. A novel biometric-enhanced authentication system, based on a trusted camera that continuously uses face recognition to verify identity, is described and evaluated in the context of Linux. With cryptographically-signed messages and continuous authentication, the difficulty of bypassing desktop authentication can be significantly increased.
National Institute of Justice (NIJ) Requirements Definition and Technical Assistance
Personal Author(s): DeCarlo, Robert L
Report Date: Nov 1999
Descriptors: (U) *LAW ENFORCEMENT, *CRIMINAL JUSTICE SYSTEM, DATA MANAGEMENT, INFORMATION SYSTEMS, TIME SERIES ANALYSIS, TRACKING, IDENTIFICATION, COMPUTER APPLICATIONS, ACOUSTIC SIGNALS, SPEECH RECOGNITION, VIDEO SIGNALS, SECURE COMMUNICATIONS, CONCEALMENT, ORDNANCE LOCATORS
Identifiers: (U) NLBCTC-NE(NATIONAL LAW ENFORCEMENT AND CORRECTIONS TECHNOLOGY CENTER-NORTHEAST), COMPUTER FORENSICS, WUAFRLNIJRQF02
Abstract: (U) The mission of the National Law Enforcement and Corrections Technology Center Northeast Region (NLECTC-NE), in conjunction with the Air Force Research Laboratory/Information Directorate (AFRL/IF), is to facilitate the identification, development, and adoption of new products and technologies specifically designed for law enforcement, corrections, and other criminal justice applications. The current technology thrust areas for the Northeast Region are Concealed Weapons Detection, Secure Communication, Timeline Analysis, Computer Forensics, Passive Location Tracking and Tagging, Audio/Video Processing, Information Management, Automatic Speaker Recognition, Automatic language Translation and Facial Recognition. This report outlines the major accomplishments of the NLECTC-NE under the Decision-Science Applications (DSA), Inc. Task Ordering Contract (TOC), and identifies on-going technology efforts.
United States Navy Implementation of Department of the Defense (DOD) Public Key Infrastructure (PKI).
Personal Author(s): Michelsen, Christopher J
Report Date: Sep 1999
Descriptors: (U) *CRYPTOGRAPHY, *ELECTRONIC SECURITY, *BIOMETRY, DEPARTMENT OF DEFENSE, STRATEGY, INFORMATION SYSTEMS, DISTRIBUTION, NAVY, THESES, RESOURCES, INFRASTRUCTURE
Identifiers: (U) PKI(PUBLIC KEY INFRASTRUCTURE)
Abstract: (U) Information assurance (IA) within DoD is becoming an increasingly difficult task as information resources are moving toward a web-based environment to counter this problem, DoD is mandating that all services implement DoD Public Key Infrastructure (PKI). DoD PKI is part of DoD's defense in depth strategy. It leverages the power of public key cryptography and digital certificates to improve IA. The thesis begins with a presentation of background information on public/private key cryptography and the elements of a PKI. The thesis then discusses those PKI management issues, i.e., CRLs and directories, that an IT manager should consider when implementing a PKI. The thesis then outlines the three areas the Navy should focus on as it implements DoD PKI; specifically PKI implementation strategies, key distribution alternatives, and how to manage change. In response to the first two areas, the author recommends regionalization, based upon the NMCI architecture, smart cards, and biometrics as answers. In response to the third area, the reader is provided with a discussion on managing change. as it relates to the implementation of DoD PKI. The thesis is concluded with a discussion of what the Navy and DoD needs to do in order to implement the ideas presented in this thesis.
Charging Ahead into the Next Millennium: Proceedings of the Systems and Technology Symposium (20th) Held in Denver, Colorado on 7-10 June 1999
Report Date: Jun 1999
Descriptors:(U) *MILITARY CAPABILITIES, *BIOLOGICAL WARFARE, SYMPOSIA, THREAT EVALUATION, BIOTECHNOLOGY, BIOMETRY, MEDICAL ENGINEERING, SMART TECHNOLOGY
Identifiers: (U) PROCEEDINGS, BRIEFING CHARTS ONLY, BIOSENSORS
Genetically Optimised Feedforward Neural Networks for Speaker Identification
Personal Author(s): Price, Richard, Willmore, Jonathan, Roberts, William
Report Date: May 1999
Descriptors: (U) *NEURAL NETS, *SPEECH RECOGNITION, *ARTIFICIAL INTELLIGENCE, IDENTIFICATION SYSTEMS, PATTERN RECOGNITION, SPEECH TRANSMISSION, AUSTRALIA, VOICE COMMUNICATIONS, SPEECH ARTICULATION, WORD RECOGNITION
Identifiers: (U) FOREIGN REPORTS
Abstract: (U) The problem of establishing the identity of a speaker from a given utterance has been conventionally addressed using techniques such as Gaussian Mixture Models (GMMs) that model the characteristics of a known speaker via means and covariances. In this paper we pose the task as a binary classification problem, and whilst in principle any one of a number of classifiers could be applied, this work compares the performance of genetically optimized neural networks versus the conventional approach of GMMs. The test data used in the experiments was the data used for the 1996 National Institute for Standards Technology (MST) evaluation of speaker identification systems.
Personal Author(s): Higgins, Alan, Benson, Peter, Li, K P, Porter, Jack
Report Date: Apr 1999
Descriptors: (U) *COMPUTER PROGRAMS, *DIALECTS, ALGORITHMS, LITERATURE SURVEYS, IDENTIFICATION, SPEECH RECOGNITION, VOICE COMMUNICATIONS
Identifiers: (U) *LANGUAGE IDENTIFICATION, DIALECT IDENTIFICATION, PE35885G, WUAFRL1049L002
Abstract: (U) The objective of this work was to develop and evaluate a capability to automatically determine the dialect spoken in samples of recorded speech. Language identification (LID) software automatically determines the language spoken in samples of recorded speech. ITTI had developed several LID programs when the testing phase of this effort began, the two most important being a "speaker dependent" and a "speaker independent" version. Both of these programs served as baseline systems. In broad terms, this effort had as one objective the testing of pre-existing LID algorithms on a dialect identification (DID) task, and subsequent development of a baseline system to improve its DID performance as another objective. The testing was specifically required to assess the effect on DID performance as another objective. The testing was specifically required to assess the effect on DID performance (i.e., accuracy) of operating parameters known to be important in tactical applications of speech-related automatic recognition algorithms, including speech segment duration, signal-to-noise ratio (SNR), bandwidth, amount of available dialect sample data, and spectral tilt variations such as those which are introduced by various communications channels. At the outset of the effort, ITTI was directed to consider wholly new approaches to DID, apart from the techniques previously found useful for automatic LID and incorporated in the pre-existing LID programs. Priority was to be given to consideration of the findings of academic dialectologists, by examining the technical dialectology literature in hopes of finding additional, new approaches to automatic DID. A literature survey and analysis of the potential of what was found there for automatic DID was therefore also a high priority objective of this effort.
Modeling Chemical Absorption Through Membranes.
Personal Author(s): Hemmes, Jeffrey M
Report Date: Mar 1999
Descriptors: (U) *DRUGS, *BIOMETRY, *PHARMACOLOGY, *TRANSDERMAL ABSORPTION, MEMBRANES(BIOLOGY), PERMEABILITY, PREDICTIONS, RATS, HUMANS, BIOCHEMISTRY, THESES, PENETRATION, SKIN(ANATOMY), BUTYL RUBBER
Identifiers: (U) DBM(DIBROMOMETHAN), PBPK(PHYSIOLOGICALLY BASED PHARMACOKINETIC)
Abstract: (U) Understanding the processes involved in dermal penetration of chemicals and drugs is important to both toxicologists and pharmacologists. Researchers developing new drugs are interested in enhancing the penetration of chemicals through the skin, while environmental professionals are interested in limiting such penetration. For both types of applications, predictive biologically-based mathematical models can be very useful in understanding the processes involved, particularly when such models are based on physiological and biochemical parameters which can be measured experimentally. In this thesis we study two existing physiologically-based pharmacokinetic (PBPK) models that predict concentrations of neat and aqueous dibromomethane (DBM) absorbed into and through different types of membranes, namely rat skin and butyl rubber. We evaluate the models and add modifications as necessary to improve the predictions. Nearly all of the parameters in these two models are measured experimentally in a laboratory. Sensitivity analysis on the permeability coefficient, the only parameter that is estimated, shows how much of an effect that parameter has on the models' predictions. The objective in studying and developing these models is to gain a better understanding of the absorption process by first modeling simple membranes such as butyl rubber, and extrapolating the results for rat skin to other species such as humans.
Convolution Methods for Mathematical Problems in Biometrics
Personal Author(s): Frenzen, Christopher L
Report Date: 15 Jan 1999
Descriptors: (U) *BIOMETRY, *CONVOLUTION, FOURIER TRANSFORMATION, FUNCTIONS, METHODOLOGY, PROBABILITY DISTRIBUTION FUNCTIONS, ONE DIMENSIONAL, PROBABILITY DENSITY FUNCTIONS, MATHEMATICS, MULTIPURPOSE
Abstract: (U) Estimation of the impostor probability density function from the inter-template and template-sample probability density functions involves a multi-dimensional convolution of the latter density functions. We assume isotropy of the probability distribution functions and use the Fourier transform to express the convolution as a one-dimensional integral with a kernel given by a spherical Bessel function.
Matching Pursuit Filters Applied to Face Identification
Personal Author(s): Phillips, P J
Report Date: Oct 1998
Descriptors: (U) *IMAGE PROCESSING, *PATTERN RECOGNITION, *WAVELET TRANSFORMS, DATA BASES, ALGORITHMS, NEURAL NETS, MATHEMATICAL FILTERS, INFRARED IMAGES, MATCHED FILTERS, FACE(ANATOMY)
Identifiers: (U) FACE RECOGNITION, PE62120A
Abstract: (U) A face identification algorithm is presented that automatically processes an unknown image by locating and identifying the face. The heart of the algorithm is the use of pursuit filters. A matching pursuit filter is an adapted wavelet expansion, where the expansion is adapted to both the data and the pattern recognition problem being addressed. For identification, the filters find the features that differentiate among faces, whereas for detection, the filters encode the similarities among faces. The filters are designed through a simultaneous decomposition of a training set into a two-dimensional wavelet expansion. This yields a representation that is explicitly two-dimensional and encodes information locally. The algorithm uses coarse to fine processing to locate a small set of key facial features, which are restricted to the nose and eye regions of the face. The result is an algorithm that is robust to variations in facial expression, hair style, and the surrounding environment. Based on the locations of the facial features, the identification module searches the database for the identity of the unknown face using matching pursuit filters to make the identification. The algorithm was demonstrated on three sets of images. The first set was images from the FERET database. The second set was infrared and visible images of the same people. (These two sets allowed the examination of algorithm performance on infrared and visible images individually, and on fused data from both modalities.) The third set of images was mugshot data from a law enforcement application.