Showing papers on "Biometrics published in 1998"

Integrating faces and fingerprints for personal identification

Abstract: An automatic personal identification system based solely on fingerprints or faces is often not able to meet the system performance requirements. We have developed a prototype biometrics system which integrates faces and fingerprints. The system overcomes the limitations of face recognition systems as well as fingerprint verification systems. The integrated prototype system operates in the identification mode with an admissible response time. The identity established by the system is more reliable than the identity established by a face recognition system. In addition, the proposed decision fusion scheme enables performance improvement by integrating multiple cues with different confidence measures. Experimental results demonstrate that our system performs very well. It meets the response time as well as the accuracy requirements.

On enabling secure applications through off-line biometric identification

Abstract: In developing secure applications and systems, designers must often incorporate secure user identification in the design specification. In this paper, we study secure off-line authenticated user identification schemes based on a biometric system that can measure a user's biometrics accurately (up to some Hamming distance). The presented schemes enhance identification and authorization in secure applications by binding a biometric template with authorization information on a token such as a magnetic strip. Also developed are schemes specifically designed to minimize the compromising of a user's private biometrics data, encapsulated in the authorization information, without requiring secure hardware tokens. We also study the feasibility of biometrics performing as an enabling technology for secure systems and applications design. We investigate a new technology which allows a user's biometrics to facilitate cryptographic mechanisms.

Biometrics, Personal Identification in Networked Society: Personal Identification in Networked Society

Abstract: From the Publisher: Biometrics: Personal Identification in Networked Society is a comprehensive and accessible source of state-of-the-art information on all existing and emerging biometrics: the science of automatically identifying individuals based on their physiological or behavioral characteristics.. "Biometrics: Personal Identification in Networked Society is an invaluable work for scientists, engineers, application developers, systems integrators, and others working in biometrics.

Personal identification system

Abstract: A portable, hand-held personal identification device for providing secure access to a host facility includes a biometric sensor system capable of sensing a biometric trait of a user that is unique to the user and providing a biometric signal indicative of the sensed biometric trait. A processing unit responsive to the biometric signal is adapted to compare the biometric signal with stored biometric data representative of the biometric trait of an enrolled person that is unique to the enrolled person, and to provide a verification signal only if the biometric signal corresponds sufficiently to the biometric data to verify that the user is the enrolled person. The verification signal includes information indicative of the enrolled person or the device. A communication unit, including a transmitting circuit, is adapted to transmit the verification signal to a host system.

Integrating Faces and Fingerprints for Personal Identification

Abstract: An automatic personal identification system based solely on fingerprints or faces is often not able to meet the system performance requirements. Face recognition is fast but not reliable while fingerprint verification is reliable but inefficient in database retrieval. We have developed a prototype biometric system which integrates faces and fingerprints. The system overcomes the limitations of face recognition systems as well as fingerprint verification systems. The integrated prototype system operates in the identification mode with an admissible response time. The identity established by the system is more reliable than the identity established by a face recognition system. In addition, the proposed decision fusion schema enables performance improvement by integrating multiple cues with different confidence measures. Experimental results demonstrate that our system performs very well.

Biometric encryption using image processing

Abstract: Biometric EncryptionTM is an algorithm which has been developed to securely link and retrieve a digital key using the interaction of a biometric image, such as a fingerprint, with a secure block of data, known as a BioscryptTM. The key can be used, for example, as an encryption/decryption key. The BioscryptTM comprises a filter function, which is calculated using an image processing algorithm, and other information which is required to first retrieve, and then verify the validity of, the key. The key is retrieved using information from an output pattern formed via the interaction of the biometric image with the filter function. Therefore, the filter function must be designed so that it produces a consistent output pattern (and thus, key). The filter function must also be designed to be secure (i.e. information about the fingerprint cannot be retrieved from the filter function). The consistency of the output pattern and the security of the filter function are the two topics discussed in this paper.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Remote authentication system

Abstract: To obtain a remote authentication system that securely authenticates with protecting biometrics information, which is user's personal information, and is firm on security when performing authentication of a person with the biometrics information, and a remote authentication method. The present invention encrypts biometrics information that is user's personal information, and transfers the biometrics information over a network in such a state that only an authentication server, which the user assigns, can decode the biometrics information. Therefore, it is possible to securely protect user's privacy that is the biometrics information in a style of reflecting user's intention, and to prevent reuse of invalid authentication information since it is possible to confirm the date and time, when the authentication information was generated, by the authentication server. Furthermore, it is possible to keep the security of a system firm since an authenticated side can confirm whether the user is authenticated.

User authentication in a communication system utilizing biometric information

Abstract: A method and apparatus for authenticating subscriber units (30) and users (25) in a communications system includes a communications node (200) which receives biometric information describing a user (25), and measures an RF signature of the subscriber unit (30). The biometric information and RF signature are compared against a valid user profile to determine authenticity of the user (25) and the subscriber unit (30). The biometric information can include retinal scan data, fingerprint data, or other data. The RF signature can include spectral content, phase or frequency characteristics, or other identifying features.

Biometric security encryption system

Abstract: A method of registering biometric data is disclosed wherein a registration profile is formed of those templates that have a likelihood of registering with the biometric data that is within predetermined limits. The profile is then compared against one or more other profiles to determine an individual most likely to have said profile. That individual is then identified. Optionally, the profile comparison is used in conjunction with a individual registration values formed by comparison between the biometric data and stored templates.

Biometric system and techniques suitable therefor

Abstract: A biometric system and method (10, 30, 40) for eliciting a migrating biometric characteristic from individuals (45). The system and method including storing device (50) for storing at least first and second templates of at least one migrating biometric characteristic for each of a population of individuals (45), the first template being a reference sample of an individual's biometric characteristic and the second template being initially derived from the first template. Device (10) for comparing an individual's first and second templates to a fresh sample provided by the individual (45), and if the fresh sample is found to sufficiently resemble the first and second templates, modifying the second template to take into account differences between the reference sample and the fresh sample.

Apparatus and methods for providing repetitive enrollment in a plurality of biometric recognition systems based on an initial enrollment

Abstract: Apparatus for providing repetitive enrollment in a plurality of biometric recognition systems based on an initial enrollment is provided. The apparatus includes an extractor for extracting a biometric attribute from a user. Further, a server is included, operatively coupled to the extractor, for interfacing with the plurality of biometric recognition systems to receive requests for biometric attributes therefrom and transmit biometric attributes thereto. The server has a memory device for storing the biometric attribute.

Self-service kiosk with biometrics verification and/or registration capability

Abstract: A self-service kiosk (1) includes a biometrics data input (3) for inputting biometrics of a user of the kiosk, a reader (2) for recovering biometrics data stored on a portable storage device such as an optical card, the portable storage device also containing information necessary to carry out a transaction, and a controller capable of comparing the input biometrics data with the stored biometrics data and authorizing a transaction based on a result of the comparison. Alternatively, or in addition to the above, the self-service kiosk may include a device for capturing an image of a customer/registrant, a biometrics capture device, and a data input device for enabling registration information to be entered and stored on a portable storage device such as an optical memory card together with the image and/or biometrics data, the portable storage device being dispensed to the customer/registrant immediately upon registration.

Automatic personal identification using fingerprints

Abstract: An accurate automatic personal identification is critical in a wide range of application domains such as national ID card, electronic commerce, and automated banking. Biometrics, which refers to automatic identification of a person based on her physiological or behavioral characteristics, is inherently more reliable and more capable in differentiating between an authorized person and a fraudulent imposter than traditional methods such as passwords and PIN numbers. Automatic fingerprint identification is one of the most reliable biometric technology. In this thesis, our objective is to design a fingerprint-based biometric system which is capable of achieving a fully automatic "positive personal identification" with a high level of confidence. We have identified and explored the following issues: (i) feature extraction finding representative features from an input image for the purpose of fingerprint matching, (ii) image enhancement--improving the clarity of ridge structures of fingerprint images to facilitate automatic extraction of features or for visual inspection, (iii) minutiae matching--determining whether two sets of features (minutiae patterns) are extracted from the same finger, (iv) integration of multiple biometrics--improving the performance of a biometric system by combining several biometrics (e.g. fingerprint, face, speech, etc.), and (v) fingerprint classification--assigning a fingerprint into one of several pre-specified categories according to its pattern formation. We have designed two prototype biometric systems: (i) a verification system which uses only fingerprints to authenticate the identity claimed by a user, and (ii) an integrated identification system which combines face recognition and fingerprint verification to make a personal identification. Our systems have been evaluated extensively on a large number of fingerprint images captured with the traditional inked method and more recent inkless optical scanners. Experimental results show that our systems perform very well on these data sets.

Identification and security using biometric measurements

Abstract: The present invention makes it possible for a user to have a security key (210) created from one or more biometric elements of the user, such as a fingerprint (204). For example, a biometric feature or combination of biometric features of the user can be used to create an instance of a problem which can only be solved by data inherent in the biometric feature or combination of biometric features. The user can supply the data to solve the problem by inputting, through an appropriate input device (101), an image, or other representation of the biometric elements from which the data that will solve the instance of the problem is derived. If the problem is solved, either completely or partially, using the derived data then the identity of the user can either be verified or ascertained. The solution can then be used for other purposes such as the generation of a cryptographic key (210).

Method of gathering biometric information

Abstract: In the past, user authorization based on biometric information was conducted by correlating a single instance of biometric information against a template. By using this method, a percentage of the population is difficult to authenticate. Further, due to skin damage and injuries, sometimes biometric information is not suited to identification. A sore throat affecting voice information and scraped finger tips affecting fingerprint information are two examples of common problems with authorization in dependence upon biometric information. A method of authenticating a user in dependence upon biometric input information is disclosed. The method allows a user to select biometric information sources and a number of repetitions for each source in order to customize the process of biometric user authentication.

Secure and dynamic biometrics-based token generation for access control and authentication

Abstract: A computer network includes at least one client computer coupled to a server computer that dynamically changes a user's password each time the user logs on to the computer network. By changing the password during the log on process, network security is increased. The server computer includes a users databases that contains a password, a username (if desired) and a biometrics template value associated with each user registered to access the computer network. A biometrics sensing device, such as a fingerprint sensor, is connected to each client computer. The user attempts to log on the server by entering a username which is optional and activating the biometrics sensing device. Appropriate software and/or hardware in the client and server computers capture a sample from the biometrics sensing device and create a template value from the captured sample. The template value thus is representative of a bodily characteristic of the user who activated the biometrics sensing device in an attempt to log on to the server computer. The client computer then transmits the template value to the server which compares the template value received from the client computer with template values previously stored in the users database. If a match is found, the log on process completes. At some point during or after the log on process, the biometrics account manager changes the current password associated with the user to a new password and overwrites the previous password with the new password.

Method for secure key management using a biometric

Abstract: This invention describes a secure method for consistently reproducing a digital key using a biometric, such as a fingerprint. The digital key is linked to the biometric only through a secure block of data, known as the protected filter. The key cannot be released from the protected filter other than via the interaction with the correct biometric image. Once generated, the digital key may be used in a system as an encryption/decryption key, or as a personal identification number (PIN).

Biometric characteristic vehicle control system having verification and reset features

Abstract: A control system for a vehicle includes a controller for learning a unique biometric characteristic of an individual to define a learned individual capable of causing performance of a function associated with the vehicle, for example. The controller performs biometric characteristic verification to generate an indication relating to whether a new individual has been learned by the controller. The control system is advantageously used, in one embodiment, for a vehicle security system. Biometric characteristic verification may also be incorporated in a remote keyless entry system, and remote engine starting system, for example. In one embodiment, the biometric characteristic verification is based upon the controller being recently entered into the biometric characteristic learning mode. According to another embodiment, the biometric characteristic verification is based upon a number of learned individuals, a change in that number, or a change in a learned biometric characteristic. The indication may be provided at the vehicle or remote therefrom by any of a light, a visual display, a vibration transducer, a speech message generator, and an audible signal generator, for example. A previous set of authorized biometric characteristics may be readily reset or restored to operate the system if unauthorized biometric characteristics have been more recently added.

Biometric Encryption: enrollment and verification procedures

Abstract: Biometric EncryptionTM is an algorithm which has been developed to securely link and retrieve a digital key using the interaction of a biometric image, such as a fingerprint, with a secure block of data, known as a BioscryptTM. The key can be used, for example, as an encryption/decryption key. The Bioscrypt comprises a stored filter function, produced by a correlation-based image processing algorithm, as well as other information which is required to first retrieve, and then verify the validity of, the key. The process of securely linking a key with a biometric is known as enrollment, while the process of retrieving this key is known as verification. This paper presents details of the enrollment and verification procedures.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Biometrics: A new era in security

Abstract: However, these security methods have important weaknesses—they can be lost, stolen, forged, or forgotten. Biometric technology would change security and access control by providing systems that recognize us by our biological or behavioral characteristics, such as fingerprints, iris patterns, facial characteristics , and speech patterns. A biometric security system uses one or more sensors (such as a camera or microphone) to acquire a sample of a physical or behavioral characteristic of someone who desires entry to a computer network, building, or other secure system. The biometric system then classifies the sample in some unique way and compares it to classifications for one or more authorized users in a database. Referring to biometric technology, Jackie Fenn, an analyst with the Gartner Group, a market research firm, said, \" It is becoming more credible based on some real-world deployments. \" In fact, Erik Bowman, an industry analyst with CardTech/SecurTech—which offers conferences, market research, and consulting services on smart-card and security technology—predicted the growing demand for network security will help increase the worldwide market for bio-metrics applications from $24 million in 1997 to $60 million in 1999. Past and projected sales figures are shown in Figure 1. The primary concerns about the technology are cost, accuracy, security, inter-operability, and intrusiveness on the people who are subject to biometric scanning. However, in the face of rapidly increasing demand for the technology, researchers and vendors are working on ways to address these concerns. In the late 1970s, security-conscious and technologically sophisticated organizations , such as the US Central Intelligence Agency and Department of Defense, began using electronic biomet-ric technology (like fingerprint-recognition systems) to guard access to such secure facilities as nuclear reactors. The technology Today, most biometric systems capture data about biological or behavioral characteristics via cameras or microphones and relay the data to a digital signal processor (DSP) for analysis, digitization, and processing. Most biometric systems conduct a verification process, in which they take processed data from a person claiming to be an authorized user and compare it to stored data for the actual user. Because this requires comparison to just one stored file, verification systems generally use a relatively simple database. On the other hand, biometric identification applications—which read a person's biological or behavioral characteristics and try to find a match from data stored for hundreds or even thousands of authorized users—can be quite complex. For example, identification applications require sophisticated databases and …

Biometric image processing and recognition

Abstract: Biometric-based identification and verification systems are poised to become a key technology, with applications including controlling access to buildings and computers, reducing fraudulent transactions in electronic commerce, and discouraging illegal immigration. There are at least eight image-based biometrics that are being actively considered. In image-based biometrics, the biometrie signature is acquired as an image and the image is processed using techniques from computer vision, image understanding, and pattern recognition. We consider two promising image-based biometrics, faces and fingerprints. For each, we provide a critical assessment of the state of the art, suggest future research directions, and identify technological challenges.

Voice recognition using neural networks

Abstract: One solution to the crime and illegal immigration problem in South Africa may be the use of biometric techniques and technology. Biometrics are methods for recognizing a user based on unique physiological and/or behavioural characteristics of the user. This paper presents the results of ongoing work into using neural networks for voice recognition.

System and method for compressing biometric models

Abstract: A system and method for building compressed biometric models and performing biometric identification using such models. The use of the compressed biometric models results in a significant decrease in the storage requirements for biometric models in conventional biometric systems. A given number of L reference biometric models are built. The L reference models are randomly divided into M subsets. During user enrollment, distance measurements between a temporary biometric model and each of the reference models in the M subsets are computed. The rank and distance parameters are used to build the compressed biometric models in accordance with the model: I(Mj, Ri, D(Mj, Ri)), where I represents the identity of the closest reference model in a corresponding subset Mj; Ri refers to the ranking of the closeness of the reference model to the temporary biometric model as compared with the closeness of each of the other reference models in the corresponding subset Mj; and D refers to the corresponding distance measure between the reference model and the temporary biometric model.

A verification protocol and statistical performance analysis for face recognition algorithms

Abstract: Two key performance characterization of biometric algorithms (face recognition in particular) are (1) verification performance and (2) and performance as a function of database size and composition. This characterization is required for developing robust face recognition algorithms and for successfully transitioning algorithms from the laboratory to real world. In this paper we (1) present a general verification protocol and apply it to the results from the Sep96 FERET test, and (2) discuss and present results on the effects of database size and variability on identification and verification performance.

User verification system

Abstract: The invention relates to a biometric verification system for use e.g. in an ATM (10). When a user wishes to use the ATM, the system scans a biometric feature of the user such as the iris of one of his eyes (32), and produces a diffraction pattern of that feature. The diffraction pattern is compared against a reference matched spatial filter in a Vander Lugt optical correlator (70). If the diffraction pattern and the matched spatial filter match then a correlation dot is produced, and the user is authorized to use the ATM (10). For a user to be able to use ATMs that comprise this verification system, he has first to use a recording system that produces the reference matched spatial filter of the biometric feature.

Use of biometrics as a methodology for defining components for ECC encryption

Abstract: A method for defining the elliptic curve for purposes of elliptic curve encryption using biometrics such as a fingerprint to define the elliptic curve equation's coefficients

Camera-Based ID Verification by Signature Tracking

Abstract: A number of vision-based biometric techniques have been proposed in the past for personal identification. We present a novel one based on visual capturing of signatures. This paper describes a system based on correlation and recursive prediction methods that can track the tip of the pen in real time, with sufficient spatio-temporal resolution and accuracy to enable signature verification. Several examples and the performance of the system are shown.

Methodology and apparatus for using the human iris as a robust biometric

Abstract: The human iris possesses characteristics that make it significantly more robust for use as a biometric identifier when compared with conventional techniques such as fingerprints, face recognition or retinal scan. The iris is an overt body, thereby allowing a remote acquisition system to capture the image. Visual patterns in individual irises are highly distinctive and clearly apparent thereby minimizing the likelihood of false positives and false negatives enrollments. Such visual iris patterns are stable over time thereby requiring a single enrollment that can last over the user's lifetime. Furthermore, the digital information of the iris can be coded very effectively, requiring a modest amount of computer storage and processing. This paper describes an automated system which allows non-intrusive acquisition of quality iris images for the purposes of enrollment, verification or identification. In essence, user locale within a prescribed volume and unobtrusive gaze toward the image acquisition devices are the only engineering hardware criteria for enrollment and verification. The device operates with non- visible near infrared illumination. The initial image acquisition uses a stereo camera pair (3D vision) system to locate the subject within a relatively large operational volume. The resulting coordinates of the user's right or left eye are used to position a pan/tilt mirror and focus mechanism associated with a higher magnification camera. This camera, called the narrow field of view (NFOV) camera, is then used to acquire a high contrast fine resolution iris image which is presented to a proprietary algorithm for the generation of an 'iris code.' Finally the computed iris code is compared to a previously stored enrollment code associated with the user for verification.