Security concerns regarding the stored biometric data is impeding the widespread public acceptanc... more Security concerns regarding the stored biometric data is impeding the widespread public acceptance of biometric technology. Though a number of bio-crypto algorithms have been proposed, they have limited practical applicability due to the trade-off between recognition performance and security of the template. In this paper, we improve the recognition performance as well as the security of a fingerprint based biometric cryptosystem, called fingerprint fuzzy vault. We incorporate minutiae descriptors, which capture ridge orientation and frequency information in a minutia's neighborhood, in the vault construction using the fuzzy commitment approach. Experimental results show that with the use of minutiae descriptors, the fingerprint matching performance improves from an FAR of 0.7% to 0.01% at a GAR of 95% with some improvement in security as well. An analysis of security while considering two different attack scenarios is also presented.
Most fingerprint matching systems are based on matching minutia points between two fingerprint im... more Most fingerprint matching systems are based on matching minutia points between two fingerprint images. Each minutia is represented by a fixed number of attributes such as the location, orientation, type and other local information. A hard decision is made on the match between a pair of minutiae based on the similarity of these attributes. In this paper, we present a minutiae matching algorithm that uses spatial correlation of regions around the minutiae to ascertain the quality of each minutia match. The proposed algorithm has two main advantages. Since the gray level values of the pixels around a minutia point retain most of the local information, spatial correlation provides an accurate measure of the similarity between minutia regions. Secondly, no hard decision is made on the correspondence between a minutia pair. Instead the quality of all the minutiae matches are accumulated to arrive at the final matching score between the template and query fingerprint impressions. Experiments on a database of 160 users (4 impressions per finger) indicate that the proposed algorithm serves well to complement the 2D dynamic programming based minutiae matching technique; a combination of these two methods can reduce the false non-match rate by approximately 3.5% at a false match rate of 0.1%.
Ieee Transactions on Information Forensics and Security, 2006
Reliable information security mechanisms are required to combat the rising magnitude of identity ... more Reliable information security mechanisms are required to combat the rising magnitude of identity theft in our society. While cryptography is a powerful tool to achieve information security, one of the main challenges in cryptosystems is to maintain the secrecy of the cryptographic keys. Though biometric authentication can be used to ensure that only the legitimate user has access to the secret keys, a biometric system itself is vulnerable to a number of threats. A critical issue in biometric systems is to protect the template of a user which is typically stored in a database or a smart card. The fuzzy vault construct is a biometric cryptosystem that secures both the secret key and the biometric template by binding them within a cryptographic framework. We present a fully automatic implementation of the fuzzy vault scheme based on fingerprint minutiae. Since the fuzzy vault stores only a transformed version of the template, aligning the query fingerprint with the template is a challenging task. We extract high curvature points derived from the fingerprint orientation field and use them as helper data to align the template and query minutiae. The helper data itself do not leak any information about the minutiae template, yet contain sufficient information to align the template and query fingerprints accurately. Further, we apply a minutiae matcher during decoding to account for nonlinear distortion and this leads to significant improvement in the genuine accept rate. We demonstrate the performance of the vault implementation on two different fingerprint databases. We also show that performance improvement can be achieved by using multiple fingerprint impressions during enrollment and verification.
... extraction artifacts: The feature extraction algorithm is imperfect and introduces measuremen... more ... extraction artifacts: The feature extraction algorithm is imperfect and introduces measurement errors. ... The orientation field determined from the input image may not be very accurate and ... Paral-lel adjacent subsegments typically indicate a good quality fingerprint region; the ridge ...
International Series on Biometrics Consulting Editors Professor David D. Zhang Professor Anil K. ... more International Series on Biometrics Consulting Editors Professor David D. Zhang Professor Anil K. Jain Department of Computer Science Dept. of Computer Science& Eng. Hong Kong Polytechnic University Michigan State University Hung Horn, Kowloon, Hong Kong 3115 Engineering Bldg. East Lansing, MI 48824-1226, USA email: [email protected] Email: [email protected] In our international and interconnected information society, there is an ever-growing need to authenticate and identify individuals. Biometrics-based ...
Abstract Automating the process of postmortem (PM) identification of individuals using dental rec... more Abstract Automating the process of postmortem (PM) identification of individuals using dental records is receiving increased attention. In developing a research prototype of an Automated Dental Identification System (ADIS), research teams from multiple institutions collaborated with forensic experts from the US Federal Bureau of Investigation Criminal Justice Information Services (CJIS) division to identify the functional requirements of ADIS. A multitude of digital image processing and pattern recognition techniques were developed ...
Eurasip Journal on Advances in Signal Processing, 2008
Page 1. Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 20... more Page 1. Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2008, Article ID 579416, 17 pages doi:10.1155/2008/579416 Review Article Biometric Template Security Anil K. Jain, Karthik Nandakumar, and Abhishek Nagar ...
Proceedings of the Pattern Recognition 17th International Conference on Volume 3 Volume 03, Aug 23, 2004
In dental biometrics , the contours of teeth in dental radiographs are utilized for human identif... more In dental biometrics , the contours of teeth in dental radiographs are utilized for human identification. However, in many images, the contours of teeth are fuzzy and only partially visible. To extract the contours from these images, we propose a method based on the active contour models . A new dynamic energy is proposed for the directional snake to discriminate boundaries of adjacent teeth. Matching result shows the contours extracted with this method perform better than traditional methods.
Fingerprint identification is based on two basic premises: (i) persistence: the basic characteris... more 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 points is 6.10 × 10 −8 . These probability estimates are compared with typical fingerprint matcher accuracy results. Our results show that (i) contrary to the popular belief, fingerprint matching is not infallible and leads to some false associations, (ii) while there is an overwhelming amount of discriminatory information present in the fingerprints, the strength of the evidence degrades drastically with noise in the sensed fingerprint images, (iii) the performance of the state-of-the-art automatic fingerprint matchers is not even close to the theoretical limit, and (iv) because automatic fingerprint verification systems use only a part of the discriminatory information present in the fingerprints, it may desirable to explore additional complementary representations of fingerprints for automatic matching.
Human faces provide demographic information, such as gender and ethnicity. Different modalities o... more Human faces provide demographic information, such as gender and ethnicity. Different modalities of human faces, e.g., range and intensity, provide different cues for gender and ethnicity identifications. In this paper we exploit the range information of human faces for ethnicity identification using a support vector machine. An integration scheme is also proposed for ethnicity and gender identifications by combining the registered range and intensity images. The experiments are conducted on a database containing 1240 facial scans of 376 subjects. It is demonstrated that the range modality provides competitive discriminative power on ethnicity and gender identifications to the intensity modality. For both gender and ethnicity identifications, the proposed integration scheme outperforms each individual modality.
Proceedings 2001 International Conference on Image Processing, Feb 1, 2001
The advent of solid-state fingerprint sensors presents a fresh challenge to traditional fingerpri... more The advent of solid-state fingerprint sensors presents a fresh challenge to traditional fingerprint matching algorithms. These sensors provide a small contact area (≈ 0.6" × 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. Minutiaebased 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.
Security concerns regarding the stored biometric data is impeding the widespread public acceptanc... more Security concerns regarding the stored biometric data is impeding the widespread public acceptance of biometric technology. Though a number of bio-crypto algorithms have been proposed, they have limited practical applicability due to the trade-off between recognition performance and security of the template. In this paper, we improve the recognition performance as well as the security of a fingerprint based biometric cryptosystem, called fingerprint fuzzy vault. We incorporate minutiae descriptors, which capture ridge orientation and frequency information in a minutia's neighborhood, in the vault construction using the fuzzy commitment approach. Experimental results show that with the use of minutiae descriptors, the fingerprint matching performance improves from an FAR of 0.7% to 0.01% at a GAR of 95% with some improvement in security as well. An analysis of security while considering two different attack scenarios is also presented.
Most fingerprint matching systems are based on matching minutia points between two fingerprint im... more Most fingerprint matching systems are based on matching minutia points between two fingerprint images. Each minutia is represented by a fixed number of attributes such as the location, orientation, type and other local information. A hard decision is made on the match between a pair of minutiae based on the similarity of these attributes. In this paper, we present a minutiae matching algorithm that uses spatial correlation of regions around the minutiae to ascertain the quality of each minutia match. The proposed algorithm has two main advantages. Since the gray level values of the pixels around a minutia point retain most of the local information, spatial correlation provides an accurate measure of the similarity between minutia regions. Secondly, no hard decision is made on the correspondence between a minutia pair. Instead the quality of all the minutiae matches are accumulated to arrive at the final matching score between the template and query fingerprint impressions. Experiments on a database of 160 users (4 impressions per finger) indicate that the proposed algorithm serves well to complement the 2D dynamic programming based minutiae matching technique; a combination of these two methods can reduce the false non-match rate by approximately 3.5% at a false match rate of 0.1%.
Ieee Transactions on Information Forensics and Security, 2006
Reliable information security mechanisms are required to combat the rising magnitude of identity ... more Reliable information security mechanisms are required to combat the rising magnitude of identity theft in our society. While cryptography is a powerful tool to achieve information security, one of the main challenges in cryptosystems is to maintain the secrecy of the cryptographic keys. Though biometric authentication can be used to ensure that only the legitimate user has access to the secret keys, a biometric system itself is vulnerable to a number of threats. A critical issue in biometric systems is to protect the template of a user which is typically stored in a database or a smart card. The fuzzy vault construct is a biometric cryptosystem that secures both the secret key and the biometric template by binding them within a cryptographic framework. We present a fully automatic implementation of the fuzzy vault scheme based on fingerprint minutiae. Since the fuzzy vault stores only a transformed version of the template, aligning the query fingerprint with the template is a challenging task. We extract high curvature points derived from the fingerprint orientation field and use them as helper data to align the template and query minutiae. The helper data itself do not leak any information about the minutiae template, yet contain sufficient information to align the template and query fingerprints accurately. Further, we apply a minutiae matcher during decoding to account for nonlinear distortion and this leads to significant improvement in the genuine accept rate. We demonstrate the performance of the vault implementation on two different fingerprint databases. We also show that performance improvement can be achieved by using multiple fingerprint impressions during enrollment and verification.
... extraction artifacts: The feature extraction algorithm is imperfect and introduces measuremen... more ... extraction artifacts: The feature extraction algorithm is imperfect and introduces measurement errors. ... The orientation field determined from the input image may not be very accurate and ... Paral-lel adjacent subsegments typically indicate a good quality fingerprint region; the ridge ...
International Series on Biometrics Consulting Editors Professor David D. Zhang Professor Anil K. ... more International Series on Biometrics Consulting Editors Professor David D. Zhang Professor Anil K. Jain Department of Computer Science Dept. of Computer Science& Eng. Hong Kong Polytechnic University Michigan State University Hung Horn, Kowloon, Hong Kong 3115 Engineering Bldg. East Lansing, MI 48824-1226, USA email: [email protected] Email: [email protected] In our international and interconnected information society, there is an ever-growing need to authenticate and identify individuals. Biometrics-based ...
Abstract Automating the process of postmortem (PM) identification of individuals using dental rec... more Abstract Automating the process of postmortem (PM) identification of individuals using dental records is receiving increased attention. In developing a research prototype of an Automated Dental Identification System (ADIS), research teams from multiple institutions collaborated with forensic experts from the US Federal Bureau of Investigation Criminal Justice Information Services (CJIS) division to identify the functional requirements of ADIS. A multitude of digital image processing and pattern recognition techniques were developed ...
Eurasip Journal on Advances in Signal Processing, 2008
Page 1. Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 20... more Page 1. Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2008, Article ID 579416, 17 pages doi:10.1155/2008/579416 Review Article Biometric Template Security Anil K. Jain, Karthik Nandakumar, and Abhishek Nagar ...
Proceedings of the Pattern Recognition 17th International Conference on Volume 3 Volume 03, Aug 23, 2004
In dental biometrics , the contours of teeth in dental radiographs are utilized for human identif... more In dental biometrics , the contours of teeth in dental radiographs are utilized for human identification. However, in many images, the contours of teeth are fuzzy and only partially visible. To extract the contours from these images, we propose a method based on the active contour models . A new dynamic energy is proposed for the directional snake to discriminate boundaries of adjacent teeth. Matching result shows the contours extracted with this method perform better than traditional methods.
Fingerprint identification is based on two basic premises: (i) persistence: the basic characteris... more 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 points is 6.10 × 10 −8 . These probability estimates are compared with typical fingerprint matcher accuracy results. Our results show that (i) contrary to the popular belief, fingerprint matching is not infallible and leads to some false associations, (ii) while there is an overwhelming amount of discriminatory information present in the fingerprints, the strength of the evidence degrades drastically with noise in the sensed fingerprint images, (iii) the performance of the state-of-the-art automatic fingerprint matchers is not even close to the theoretical limit, and (iv) because automatic fingerprint verification systems use only a part of the discriminatory information present in the fingerprints, it may desirable to explore additional complementary representations of fingerprints for automatic matching.
Human faces provide demographic information, such as gender and ethnicity. Different modalities o... more Human faces provide demographic information, such as gender and ethnicity. Different modalities of human faces, e.g., range and intensity, provide different cues for gender and ethnicity identifications. In this paper we exploit the range information of human faces for ethnicity identification using a support vector machine. An integration scheme is also proposed for ethnicity and gender identifications by combining the registered range and intensity images. The experiments are conducted on a database containing 1240 facial scans of 376 subjects. It is demonstrated that the range modality provides competitive discriminative power on ethnicity and gender identifications to the intensity modality. For both gender and ethnicity identifications, the proposed integration scheme outperforms each individual modality.
Proceedings 2001 International Conference on Image Processing, Feb 1, 2001
The advent of solid-state fingerprint sensors presents a fresh challenge to traditional fingerpri... more The advent of solid-state fingerprint sensors presents a fresh challenge to traditional fingerprint matching algorithms. These sensors provide a small contact area (≈ 0.6" × 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. Minutiaebased 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.
Uploads
Papers by Anil Jain