Palm Print Recognition: A New Algorithm For Corner Detection Using Palm Anatomy Features

Abstract

This paper describes an automated approach to palm print recognition. Particular emphasis has been given to the alignment method, for which a new corner finding algorithm has been developed. The corner finding algorithm proposed in this paper is a simple and fast way to process corners and has been particularly developed to detect the fingertip and trough corners of a palm. Based on three key corners, a consistent region of interest (ROI) is extracted for each palm. A feature vector is computed for each ROI and a similarity measure is computed from for similar and dissimilar palms. It is seen that that the similarity measure is markedly variable for similar and dissimilar palms