Probability of Random Correspondence for Fingerprints

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 (nPRC) and (iii) PRC between a specific sample among n others (specific nPRC). Experimental results show that the theoretical estimates of fingerprint individuality using our model consistently follow the empirical values based on the NIST4 database.