On the Individuality of Fingerprints
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Models for Assessing the Individuality of Fingerprints
AUTOID '05 Proceedings of the Fourth IEEE Workshop on Automatic Identification Advanced Technologies
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
IWCF'10 Proceedings of the 4th international conference on Computational forensics
Latent fingerprint rarity analysis in Madrid bombing case
IWCF'10 Proceedings of the 4th international conference on Computational forensics
Hi-index | 0.00 |
Individuality of fingerprints can be quantified by computing the probabilistic metrics for measuring the degree of fingerprint individuality. In this paper, we present a novel individuality evaluation approach to estimate the probability of random correspondence (PRC). Three generative models are developed respectively to represent the distribution of fingerprint features: ridge flow, minutiae and minutiae together with ridge points. A mathematical model that computes the PRCs are derived based on the generative models. Three metrics are discussed in this paper: (i) PRC of two samples, (ii) PRC among a random set of n samples (n PRC) and (iii) PRC between a specific sample among n others (specific n PRC). Experimental results show that the theoretical estimates of fingerprint individuality using our model consistently follow the empirical values based on the NIST4 database.