An improved ridge features extraction algorithm for distorted fingerprints matching

摘要

The performance of a fingerprint matching system is affected by the nonlinear deformation introduced in the fingerprint impression during image acquisition. Many matching algorithms have been proposed to deal with the nonlinear distortions of the fingerprint images. Recently, these distortion issues can be solved by using incorporating ridge feature with minutiae. In this paper, we proposed a novel ridge feature extraction algorithm to improve the accuracy of fingerprint matching and the time of ridge feature extraction process. The experimental results show that our proposed algorithm archives 1.8 times faster than Choi's algorithm on FVC2004-DB1A, FVC2004-DB3A databases. And the equal error rate (ERR) of the ROC for Choi's one is 6.35% and it is only 5.23% for the proposed algorithm on FVC2004-DB3A database. This proved that the proposed algorithm is a reliable and effective algorithm for distorted fingerprints matching.