A Fingerprint Matching Algorithm of Minutia Based on Local Characteristic

Abstract

To overcome the adverse effect caused by shift and rotation in fingerprint matching, a new method for fingerprint minutia extraction is presented. Since the orientation field around the fingerprint core has a certain specific regularity, we extract the fingerprint reference point and reference direction based on the orientation field of the image. Then we take the reference point as the origin, and the reference direction as the polar axis to establish a polar coordinate system. The fingerprint minutia information which is constituted by minutia point type, polar coordinate and the direction of minutia point is independent of the shift and rotation of the fingerprint. Overall matching is employed here to match two fingerprint images with shift and rotation. Experiments show that this method can effectively eliminate the effects caused by shift and rotation in fingerprint matching, and can be widely used on DSP chips in real-time applications.