Singular points detection using fingerprint orientation field reliability

Abstract

Singular points detection is the most challenging and important process in biometrics fingerprint verification and identification systems. Singular points are used for fingerprint classification, fingerprint matching and fingerprint alignment. This paper overcomes problems of the previous methods of miss- deducting or deducting spurious singular points. We propose a novel algorithm for singular point detection based on the fingerprint orientation field reliability. The algorithm starts by enhancing the fingerprint image using the short time Fourier Transform analysis (STFT), followed by calculating the orientation field reliability and locating the singular points. Experimental results have proven that the proposed algorithm locates singular points in a fingerprint image with high accuracy and can even locate the secondary core and delta if they exist.