Quantitative Assessment of the individuality of friction ridge patterns

The goal of this project was to increase understanding of the discriminative power of friction ridge patterns using computational approaches. A three-pronged approach was taken: (i) a study of the fingerprints of twins using automatic fingerprint matching algorithms, (ii) modeling the probability distribution of fingerprints from which the probability of random correspondence of fingerprints is determined– this is the generative approach to individuality, and (iii) new algorithms for feature extraction and classification are used to determine error probabilities– this is the discriminative approach to individuality. The main conclusion of the twins’ study is that although friction ridge patterns of twins are more similar than in the general population, they are still discriminable. The twins’ findings strengthen the argument of fingerprint individuality. Taking the generative approach the individuality of a forensic modality can also be established by computing the probability of random correspondence of two pieces of evidence directly from the underlying probability distribution of evidence features. The distribution can be modeled as a mixture distribution whose parameters can be determined from a database of fingerprints. First a model consisting of only minutiae was considered and then expanded to include ridge information as well. It was found that the probability of random correspondence with ridges is much lower than with minutiae alone. These probabilities were quantified in terms of the available number of minutiae and ridge points. In the discriminative approach two new approaches to automatic fingerprint compar­ ison were developed: use of likelihood methods instead of ROC-based methods, and using ridge information in addition to minutiae in fingerprint comparison. Both discriminative studies point to improved performance particularly when there are fewer minutiae available in the input as in the case of latent prints. This document is a research report submitted to the U.S. Department of Justice. This report has not been published by the Department. Opinions or points of view expressed are those of the author(s) and do not necessarily reflect the official position or policies of the U.S. Department of Justice.