An Efficient Approach to Recognize Fingerprints

Abstract

Fingerprint analysis is typically based on the position and pattern of detected singular points in the fingerprint images. These singular points (cores and deltas) represent the characteristics of local ridge patterns, determine the topological structure (i.e., fingerprint type) and largely influence the orientation field. A core-delta relation is used as a global constraint for the final selection of singular points. This paper proposed an approach for singular points detection and then recognizes fingerprints based on singular points position and their relative distances. Experimental results show that the approach is efficient and robust, giving better results than existing dominant approaches.