Reference Point and Orientation Detection of Fingerprints

Abstract

In this paper we suggest a novel approach for detection of a unique reference point and computation of a unique reference orientation of fingerprints for feature extraction in polar coordinates. After finding orientation field of the fingerprint the curvature measurement is done on the result. By using this information it is possible to determine the exact location of the singular points. Based on this information finally the reference point and reference orientation will be obtained. The proposed method is of high accuracy and performance and at the meantime tolerates displacement and rotation of the input fingerprint. This can be applied to all classes of fingerprints especially to problematic arch class ones.