Maximum-Likelihood Deformation Analysis of Different-Sized Fingerprints

Abstract

This paper introduces a probabilistic formulation in terms of Maximum-likelihood estimation to calculate the optimal deformation parameters, such as scale, rotation and translation, between a pair of fingerprints acquired by different image capturers from the same finger. This uncertainty estimation technique allows parameter selection to be performed by choosing parameters that minimize the deformations uncertainty and maximize the global similarity between the pair of fingerprints. In addition, we use a multi-resolution search strategy to calculate the optimal deformation parameters in the space of possible deformation parameters. We apply the method to fingerprint matching in a pension fund management system in China, a fingerprint-based personal identification application system. The performance of the method shows that it is effective in estimating the optimal deformation parameters between a pair of fingerprints.

This paper is supported by the National Science Fund for Distinguished Young Scholars of China under Grant No. 60225008, the Special Project of National Grand Fundamental Research 973 Program of China under Grant No. 2002CCA03900, the National High Technology Development Program of China under Grant No. 2002AA234051, the National Natural Science Foundation of China under Grant Nos. 60172057, 69931010, 60071002,30270403,60072007;