Fingerprint Feature-Point Matching Based on Motion Coherence

Abstract

Fingerprint matching is very important for automatic fingerprint recognition system (AFIS). After local structure matching, one minutia in query fingerprint may have multiple candidate matching minutiae in template fingerprint. So how to get right one-to-one matching pairs has great effect on the performance of fingerprint matching algorithm. In this paper, a global fingerprint matching algorithm is presented. The main contribution of this paper is that a novel and efficient algorithm for getting one-to-one matching pairs based on motion coherence is proposed. Motion coherence is a very useful feature for fingerprint matching. The algorithm is tested on a public database FVC2002 DB1_A and FVC2004 DB1_A. Experimental results show that the proposed algorithm is performed well compared with other ones.