Probability of Random Correspondence for Fingerprints

Authors:
Chang Su;Sargur N. Srihari
Affiliations:
Computer Science and Engineering Department, University at Buffalo, Buffalo, NY, USA 14228;Computer Science and Engineering Department, University at Buffalo, Buffalo, NY, USA 14228
Venue:
IWCF '09 Proceedings of the 3rd International Workshop on Computational Forensics
Year:
2009

Citing 3
Cited 2

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)

Discovering correspondences between fingerprints based on the temporal dynamics of eye movements from experts

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.