Showing papers on "Fingerprint recognition published in 2001"

Enhancing security and privacy in biometrics-based authentication systems

Abstract: Because biometrics-based authentication offers several advantages over other authentication methods, there has been a significant surge in the use of biometrics for user authentication in recent years. It is important that such biometrics-based authentication systems be designed to withstand attacks when employed in security-critical applications, especially in unattended remote applications such as e-commerce. In this paper we outline the inherent strengths of biometrics-based authentication, identify the weak links in systems employing biometrics-based authentication, and present new solutions for eliminating some of these weak links. Although, for illustration purposes, fingerprint authentication is used throughout, our analysis extends to other biometrics-based methods.

Fingerprint matching using minutiae and texture features

Abstract: The advent of solid-state fingerprint sensors presents a fresh challenge to traditional fingerprint matching algorithms. These sensors provide a small contact area (/spl ap/0.6"/spl times/0.6") for the fingertip and, therefore, sense only a limited portion of the fingerprint. Thus multiple impressions of the same fingerprint may have only a small region of overlap. Minutiae-based matching algorithms, which consider ridge activity only in the vicinity of minutiae points, are not likely to perform well on these images due to the insufficient number of corresponding points in the input and template images. We present a hybrid matching algorithm that uses both minutiae (point) information and texture (region) information for matching the fingerprints. Results obtained on the MSU-VERIDICOM database shows that a combination of the texture-based and minutiae-based matching scores leads to a substantial improvement in the overall matching performance.

Biometrical fingerprint recognition: don't get your fingers burned

Abstract: One of the most critical issues to solve when building multi-accessible systems, such as computer applications, cars or physical buildings, is to determine the identity of a person. A system protecting confidential information, or items of value, puts strong security demands on the identification. Biometry provides us with a userfriendly method for this identification and is becoming a competitor for current identification mechanisms, especially for electronic transactions. However, there are ways to compromise a system based on biometric verification. This article focuses on the drawbacks and risks of biometric verification, specifically verification based on fingerprints. It shows how all currently available fingerprint scanners can be fooled by dummies that are created with very limited means and skills.

On the individuality fingerprints

Abstract: Fingerprint identification is based on two basic premises: (i) persistence: the basic characteristics of fingerprints do not change with time; and (ii) individuality: the fingerprint is unique to an individual. The validity of the first premise has been established. While the second premise is generally accepted to be true, the underlying scientific basis of fingerprint individuality has not been formally tested. We address the problem of fingerprint individuality by quantifying the amount of information available in minutiae points to establish a correspondence between two fingerprint images. We derive an expression which estimates the probability of falsely associating minutiae-based representations from two arbitrary fingerprints. For example, the probability that a fingerprint with 36 minutiae points will share 12 minutiae points with another arbitrarily chosen fingerprint with 36 minutiae points is 6.10/spl times/10/sup -8/. These probability estimates are compared with typical fingerprint matcher accuracy results. Our results show that: (i) fingerprint matching is not infallible and leads to some false associations, (ii) the performance of automatic fingerprint matcher does not even come close to the theoretical performance, and (iii) due to the limited information content of the minutiae-based representation, automatic system designers should explore the use of non-minutiae-based information present in the fingerprints.

Segmentation of Fingerprint Images

Abstract: An important step in an automatic fingerprint recognition system is the segmentation of fingerprint images. The task of a fingerprint segmentation algorithm is to decide which part of the image belongs to the foreground, originating from the contact of a fingertip with the sensor, and which part to the background, which is the noisy area at the borders of the image. In this paper, an algorithm for the segmentation of fingerprints is presented. The method uses three pixel features, being the coherence, the mean and the variance. An optimal linear classifier is trained for the classification per pixel, while morphology is applied as postprocessing to obtain compact clusters and to reduce the number of classification errors. Manual inspection shows that the proposed method provides accurate high-resolution segmentation results. Only 6.8% of the pixels is misclassified while the postprocessing further reduces this ratio. Experiments show that the proposed segmentation method and manual segmentation perform equally well in rejecting false fingerprint features from the noisy background. Keywords— Image processing, fingerprint image segmentation, pixel features, coherence, linear classification, neural network.

Fingerprint sensor with feature authentication

Abstract: An apparatus and method for providing user access to a secured application. In one exemplary embodiment, a detector apparatus comprises a fingerprint sensor having a receiving portion that is configured to accept an authentication article. The fingerprint sensor detects one or more predetermined features of the authentication article and reads at least a portion of a fingerprint of a user. The authentication article may include a precious gem such as a diamond. The detector apparatus may further comprise a feature detection sensor in operative relation with the fingerprint sensor. The feature detection sensor detects the one or more of the predetermined features. The fingerprint sensor may be detachably coupled to a portable device having an interface for operably communicating with a computer system to determine an identity of the user. A method, comprising: reading the fingerprint of a user with a fingerprint sensor; detecting one or more features of an authentication article with the fingerprint sensor; analyzing at least a portion of the fingerprint to derive a first indication for verifying an identity of the user; analyzing at least one of the one or more features of the authentication article to derive a second indication for authenticating the fingerprint; and combining the first and second indications for selectively providing access to the secured application to the user.

Biometric authentication device for use with a personal digital assistant

Abstract: A biometric authentication device for use with a host having memory, processing power and communication capabilities, such as a personal digital assistant (PDA). The biometric device includes a finger print module having a fingerprint sensor for capturing a user's fingerprint placed onto the fingerprint sensor. The fingerprint module is interconnected and communicates with the host PDA. The fingerprint module also includes a portion adapted to receive and read a card containing electronic fingerprint information, such as a smart card. The fingerprint module is capable of determining a match between the user's fingerprint captured from the fingerprint sensor and the electronic fingerprint information stored on the smart card. Determination of the match between the end user (and those) captured fingerprint and the electronic fingerprint information enables biometric verification or identification of the end user. This information may be transmitted via the interconnected PDA or other wireless host device. The biometric device is useful in time and attendance, access and control as well as user identification and verification applications. Application program interface software used with the biometric device permits application specific solutions to be developed for the particular PDA or other host device.

Modelling Plastic Distortion in Fingerprint Images

Abstract: This paper introduces a plastic distortion model to cope with the nonlinear deformations characterizing fingerprint images taken with online acquisition sensors. The problem has a great impact on several practical applications, ranging from the design of robust fingerprint matching algorithms to the generation of synthetic fingerprint images. The experimentation on real data validates the model and demonstrates its efficacy in registering minutiae data from highly distorted fingerprint samples.

A combination fingerprint classifier

Abstract: Fingerprint classification is an important indexing method for any large scale fingerprint recognition system or database as a method for reducing the number of fingerprints that need to be searched when looking for a matching print. Fingerprints are generally classified into broad categories based on global characteristics. This paper describes novel methods of classification using hidden Markov models and decision trees to recognize the ridge structure of the print, without needing to detect singular points. The methods are compared and combined with a standard fingerprint classification algorithm and results for the combination are presented using a standard database of fingerprint images. The paper also describes a method for achieving any level of accuracy required of the system by sacrificing the efficiency of the classifier. The accuracy of the combination classifier is shown to be higher than that of the two state-of-the-art systems tested under the same conditions.

Identity authentication device

Abstract: An identity authentication device is stylus-shaped. A processor is disposed within the device. The stylus-shaped device includes a scanner-type device component for capturing within the processor memory a written signature generated by the stylus while the stylus is writing upon a surface. A fingerprint sensor is disposed within the grip of the stylus. The fingerprint sensor enables the capture of a digital signature of the writer at the same time that the written signature of the writer is captured. Once the identity of the writer has been authenticated by comparison against a reference print, the signature of the writer irrefutable. The device serves the same general purpose and can be used in lieu of a signature pad. The device is either attached to a surface or is portable and wireless.

Improved Fingerpring Matching by Distortion Removal

Abstract: Fingerprint recognition is a well-researched problem, and there are several highly accurate systems commercially available. However, this biometric technology still suffers from problems with the handling of bad quality prints. Recent research has begun to tackle the problems of poor quality data. This paper takes a new approach to one problem besetting fingerprints — that of distortion. Previous attempts have been made to ensure that acquired prints are not distorted, but the novel approach presented here corrects distortions in fingerprints that have already been acquired. This correction is a completely automatic and unsupervised operation. The distortion modelling and correction are explained, and results are presented demonstrating significant improvements in matching accuracy through the application of the technique.

Fingerprint recognition using wavelet features

Abstract: A new method of fingerprint recognition based on features extracted from the wavelet transform of the discrete image is introduced. The wavelet features are extracted directly from the gray-scale fingerprint image with no pre-processing (i.e. image enhancement, directional filtering, ridge segmentation, ridge thinning and minutiae extraction). The proposed method has been tested on a small fingerprint database using the k-nearest neighbor (k-NN) classifier. The very high recognition rates achieved show that the proposed method may constitutes an efficient solution for a small-scale fingerprint recognition system.

Wavelet domain features for fingerprint recognition

Abstract: A fingerprint recognition approach based on features extracted from the wavelet transform of the discrete image is presented. The efficiency of the method is proven by the high recognition rates achieved using the k-nearest neighbour (k-NN) classifier. The method requires lower computational effort than most of the fingerprint recognition methods proposed to date.

Enclosure and biometric data collection for fingerprint sensor device

Abstract: The enclosure assembly comprises a stationary member including at least two substantially parallel sidewalls, the sidewalls, the sidewalls partially defining a cavity in which the fingerprint sensor is disposed. An access piece, configured to move relative to the stationary member, has a surface area larger than the surface area of the fingerprint sensor and further includes a conductive portion electrically coupled to ground. A movement apparatus is preferably mechanically coupled to the stationary member and the moveable access piece. The movement apparatus is configured to maintain the moveable access piece in a position covering the fingerprint sensor and yet to allow motion of the moveable access piece relative to the stationary member so as to expose the fingerprint sensor. According to another embodiment, a method for enrolling a composite image of an object using a fingerprint sensor is provided. According to an embodiment, the method comprises the steps of receiving a finger disposed over a fingerprint sensor in a first stationary position; capturing a first image of a first portion of the finger with the fingerprint sensor; causing the finger to be repositioned over the fingerprint sensor in a second stationary position; capturing a second image of a second portion of the finger with the fingerprint sensor; and constructing a representative image of the finger from the first and second images.

System and method for cardless secure credit transaction processing

Abstract: In one embodiment, the system and device of the present invention extracts unique numerical information from a fingerprint. A fingerprint is first scanned and the scanned image is enhanced. The blurred area of the image is restored and the enhanced image is binarized. The binarized image is then thinned. A core point in the image is detected and minutiae within a given radius from the core point are detected. A number is then extracted from the image by computing relation of minutiae to the core point. In one embodiment, the present invention provides a computer data encryption/decryption device and program that uses a fingerprint minutiae generated password to encrypt/decrypt credit card information before sending the information over a computer network. The system uses the finger print along with a public key infrastructure (PKI) and some image processing to ensure the security of the user's accounts.

Fingerprint identification method and apparatus

Abstract: A method and device for fingerprint identification implementing precise identification at a high speed by using partial images of a fingerprint obtained through relative movements of a finger to a small sized sensor are provided. For reassembling a sequence of partial images inputted from a frame input section 50 into a complete image, each of the partial images is collated with a user's fingerprint image (template image) registered in a template image storage section 52 to determine a position where the partial image matches best at an optimal position calculator 55, and then combined with a partial composite image stored in a partial composite image storage section 53 at an image combining section 60. When the complete composite image is obtained after repeating the above operations, specific features are extracted from the composite image at a reference character extracting section 62, and collated with those of the template image stored in a template reference character storage section 54. Consequently, user authentication can be performed at a high speed while ensuring stability in the collating operation.

Optical and smart card identification reader

Abstract: A biometric authentication device for use with a data card such as an optical card, a memory chip card, or a smart card. The biometric device includes a fingerprint module having a fingerprint sensor for capturing a user's fingerprint placed onto the fingerprint sensor. The biometric device includes a portion adapted to receive and read a card containing optical or electronic fingerprint information. The biometric device includes processing capabilities to determine a match between data from the user's fingerprint captured from the fingerprint sensor and the electronic fingerprint data stored on the optical or smart card. Determination of the match between the captured fingerprint data and the electronic fingerprint data enables biometric verification of identification of the end user. The biometric device is useful in time and attendance, access and control, as well as user identification and verification applications. Programmable software used with the biometric device permits application specific biometric solutions to be developed.

Method, apparatus and system for authenticating fingerprints, and communicating and processing commands and information based on the fingerprint authentication

Abstract: A fingerprint authentication and communication system having a fingerprint sensor and reader that converts a fingerprint into a digital profile output, a plurality of databases for storing among other things fingerprint digital profiles, user ID's, and patient related medical information, software that determines whether a recently entered fingerprint digital profile is on the approved list for authentication, and telecommunication transceiver for communicating user selected actions over telephone lines, wireless channels and the Internet. The system is preferably concealed in a handheld product for physicians and allows medical professionals to initiate and perform a plurality of actions, such as ordering multiple prescriptions and lab tests, with a fingerprint induced command.

Method and system for fingerprint authentication

Abstract: An improved method and system for reading and analyzing fingerprints is disclosed. According to the present invention, fingerprints are scanned and then analyzed to determine a value in dependence upon a predetermined acquisition parameter, such as for instance one of a moisture content of the fingertip and an applied fingertip pressure. The scanned fingerprint is subsequently processed to remove “false minutiae” in dependence upon the determined value, whilst retaining authentic minutiae for user authentication. Processing the fingertip to determine a condition thereof prior to image processing results in a more selective removal of minutiae, thus resulting in a larger set of minutiae being retained for comparison to a stored biometric template.

System and method for fingerprint image enhancement using partitioned least-squared filters

Abstract: In an automatic fingerprint authentication or identification system, the fingerprint image acquisition is severely effected by the limitations of the acquisition process. The two modes of input, viz. scanning inked fingerprints from paper records or directly from a finger using live-scan fingerprint scanners suffer from the following noise sources in the input in addition to standard noise in the camera. Non-uniform ink application, uneven pressure while rolling on the paper or pressing on the scanner surface and external dirt like oil and climatic variations in the moisture content of skin are some of the main causes for the ridges and valleys not to be imaged clearly. This invention deals with a method of learning a set of partitioned least-sqaures filters that can be derived from a given set of images and ground truth pairs as an offline process. The learned filters are convolved with input fingerprint images to obtain the enhanced image.

Deriving and matching image fingerprint sequences for mobile robot localization

Abstract: Proposes a method for creating unique identifiers, called fingerprint sequences, for visually distinct locations by recovering statistically significant features in panoramic color images. Fingerprint sequences are expressive enough for mobile robot localization, as demonstrated using a minimum energy sequence-matching algorithm that is described. Empirical results in two different places demonstrate the reliability of the system for global localization on a Nomad Scout mobile robot.

Biometric authentication device for use with token fingerprint data storage

Abstract: A biometric authentication device for use with a token such as button having biometric data stored thereon. The biometric device includes a fingerprint module having a fingerprint sensor for capturing a user's fingerprint placed onto the fingerprint sensor. The fingerprint module is capable of receiving and reading the token when placed on a token socket located on the biometric. device. The tokens contain user information, including electronic fingerprint information. The fingerprint module is capable of determining a match between the user's fingerprint captured from the fingerprint sensor and the electronic fingerprint information stored on the token. Determination of the match between the end user captured fingerprint and the stored electronic fingerprint information enables biometric verification or identification of the end user. Status indicators indicate to a user whether a successful match has occurred between the user supplied fingerprint and the biometric information stored on the token. The information may be transmitted to a central database and may be part of a network of biometric devices. The biometric device is useful in time and attendance, access and control as well as user identification and verification applications. Application program interface software used with the biometric device permits application specific solutions to be developed for biometric token applications.

Biometric authentication device for use in mobile telecommunications

Abstract: A biometric authentication device for use with a telecommunications device such as a wireless phone having memory, processing power and communication capabilities is disclosed. The biometric device includes a fingerprint module having a fingerprint sensor for capturing a user's fingerprint placed onto the fingerprint sensor. The fingerprint module is interconnected and communicates with the telecommunications device. The fingerprint module also includes a portion adapted to receive and read a card containing electronic fingerprint information, such as a smart card. The fingerprint module is capable of determining a match between the user's fingerprint captured from the fingerprint sensor and the electronic fingerprint information stored on the smart card. Determination of the match between the end user captured fingerprint and the stored electronic fingerprint information enables biometric verification or identification of the end user. This information may be transmitted via the interconnected telecommunications device. The biometric device is useful in time and attendance, access and control as well as user identification and verification applications. Application program interface software used with the biometric device permits application specific solutions to be developed for biometric telecommunications.

Safety holster for preventing access to a firearm by unauthorized users

Abstract: A safety holster for a firearm, including a pivotally mounted retaining member for engaging the trigger guard of the firearm and preventing withdrawal of the firearm from the holster by anyone other than an authorized user of the firearm. The holster includes a fingerprint sensor for scanning fingerprint information of a perspective user of the firearm, and a processor for comparing the scanned fingerprint information with stored fingerprint information of an authorized user and releasing the retaining member only if the scanned fingerprint information matches that of the authorized user.

Fingerprint sensor and position controller

Abstract: PROBLEM TO BE SOLVED: To provide a system for sensing a coordinate position and an identification of a finger. SOLUTION: The position and identification information sensed by a single fingerprint touch pad 400 are substantially simultaneously and continuously analyzed. Coordinate position information is used to control an eyemark on a display by a mouse driver 440 of a computer 405 as a processor and the identification information is used to limit access to a computer system by an identification system 435 of the computer 405.

Fingerprint authentication apparatus

Abstract: A fingerprint authentication apparatus has a combined visible/infrared light source, which illuminates a finger placed on an optical image sensor with both infrared light and visible light. The optical image sensor has a block with infrared sensitivity and a block within infrared sensitivity, and generates a fingerprint image from light scattered by the finger. The infrared sensitivity of the infrared-sensitive block of the optical image sensor is such that a clear image is obtained from a living organism, and an unclear image is obtained from a replica. If the finger is an actual living finger, the fingerprint images from both blocks are clear, but in the case of a replica, the image from the block having infrared sensitivity is clear, and the image from the block without having infrared sensitivity is unclear. A reference processing section compares the clarity of the fingerprint images from the block with infrared sensitivity and the block without having infrared sensitivity, and if there is a difference therebetween, judges that the finger was a replica. After this is done, an image processing section 14 extracts minutiae from the fingerprint image, and a comparison section compares the fingerprint data with fingerprint in a database.

Remote control with the fingerprint recognition capability

Abstract: Disclosed is a method and system for controlling access to a television set using a remote control unit having a finger verification means. The method includes the steps of: placing at least one finger on the remote control unit for scanning; obtaining fingerprint data indicative of the scanned finger; comparing the fingerprint data to predetermined reference data to establish a fingerprint match; and, if a match is established, providing access to a number of channels associated with the scanned finger. The system includes a fingerprint reader for generating fingerprint data; a processor programmed to prompt the user to enter fingerprint data; and, a fingerprint recognition means for verifying that the user is an authorized user of the remote control apparatus.

Fingerprint classification using an AM-FM model

Abstract: Research on fingerprint classification has primarily focused on finding improved classifiers, image and feature enhancement, and less on the development of novel fingerprint representations. Using an AM-FM representation for each fingerprint, we obtain significant gains in classification performance as compared to the commonly used National Institute of Standards system, for the same classifier.