Reference point estimation in fingerprint image

Due to different imaging conditions, a fingerprint image may suffer from problems like translation, rotation, scaling and elastic distortion. A fingerprint recognition algorithm should address these problems for efficiency. One solution is to uniquely detect a reference point and align the fingerprint image based on the detected reference point. Accurate estimation of reference point is one of the major challenges in an automatic fingerprint recognition system. This paper presents a novel method to estimate a reference point for all types of fingerprints by tracing the chain coded contour of a fingerprint image. Chain codes are used to represent an image contour by a connected sequence of straight line segments of specified length and direction. The algorithm identifies the unique reference point as the point of maximum curvature changes in the fingerprint convex ridges. Experimental results show that our proposed algorithm can uniquely estimate a reference point for all types of fingerprints.