A feature purification algorithm of fingerprint verification

Most of the current fingerprint identification and verification systems are based on minutiae matching. The minutiae are normally ridge bifurcations and terminations which are usually detected in the thinned binary image of the fingerprint. Due to the presence of noise as well as different preprocessing method the thinned image contains a large number of false minutiae which may highly decrease the matching performance and increase the matching time. In this paper, we propose a new algorithm for feature purification which combines the image quality information and structural analysis to remove the false minutiae. Experimental results show that the performance of the proposed algorithm is good.