Fingerprint Texture Feature for Discrimination and Personal Verification

Fingerprint is a reliable biometric which is used for personal verification. Current fingerprint verification techniques can be broadly classified as Minutiae-based, ridge feature-based and correlation-based each having its own merits and demerits. In this paper, we propose use of the statistical texture analysis of a fingerprint using spatial grey level dependence method (SGLDM) for discrimination and personal verification. This method extracts texture features by an algorithm based on the spatial grey level dependence method. The fingerprint images were randomly chosen from the fingerprint databases of FVC 2000 and FVC2002. Results show that fingerprint texture feature can be reasonably used for discrimination and for personal verification.