Biometrics - Fingerprint Overview

Uniqueness of fingerprints is widely accepted among the scientific community; this has formed a basis for their constituting a physical evidence of the individuality. An automatic fingerprint identification system (AFIS) essentially determines (with as little human intervention as possible) whether two given fingerprints are alike. We are developing a state of the art application of AFIS in the context of disbursement of social benefits. Here, the purpose of the AFIS is to avoid "double dipping" - the same person claiming the benefits under two different identities.
Matching entire fingerprint images is neither effective nor efficient; useful features need to be extracted from a given fingerprint image for reliable matching. The features of the fingerprint are called minutia - typically the locations where a fingerprint ridge terminates or bifurcates. These features are matched with the features extracted from the other fingerprints.
We are also working on ways of enhancing the security and privacy of fingerprint systems. One method involves challenge/response and information hiding in compressed images to guarantee the liveliness of an acquired image. This helps prevents replay attacks. Another technique is Cancelable Biometrics.

Selected publications:

Biometrics 101
R. M. Bolle, J. H. Connell, S. Pankanti, N. K. Ratha, A. Senior
IBM Research Report, Computer Science, RC22481, June 2002.

There is much interest in the use of biometrics for verification, identification, and "screening" applications, collectively called biometric authentication. This interest has been heightened because of the threat of terrorism. Biometric authentication systems offer advantages over systems based on knowledge or possession such as unsupervised (legacy) authentication systems based on password/PIN and supervised (legacy) authentication systems based on driver's licences and passports. The most important advantage is increased security: when a person is authenticated based on a biometric, the probability that this person is the originally enrolled person can be statistically estimated or computed in some other way. When a person is authenticated based on a password or even based on human observation, no such probabilities can be determined. Of course, the mere capability to compute this probability is not sufficient, what is needed is that the probability of correct authentication is high and the error probabilities are low. Achieving this probabilistic linking by introducing biometrics in authentication systems brings along many design choices and may introduce additional security loopholes. This document studies the many aspects of biometric applications that are an issue even before a particular biometrics has been selected; it further studies many issues that are associated with the currently popular biometric identifiers, namely, finger, face, voice, iris, hand (geometry) and signature.