Palmprint verification with moments

Abstract

Palmprint verification is an approach for verifying a palmprint input by matching the input to the claimed\nidentity template stored in a database. If the dissimilarity measure between the input and the claimed template is\nbelow the predefined threshold value, the palmprint input is verified possessing same identity as the claimed\nidentity template. This paper introduces an experimental evaluation of the effectiveness of utilizing three well\nknown orthogonal moments, namely Zernike moments, pseudo Zernike moments and Legendre moments, in the\napplication of palmprint verification. Moments are the most commonly used technique in character feature\nextraction. The idea of implementing orthogonal moments as palmprint feature extractors is prompted by the fact\nthat principal features of both character and palmprint are based on line structure. These orthogonal moments are\nable to define statistical and geometrical features containing line structure information about palmprint. An\nexperimental study about verification rate of the palmprint authentication system using these three orthogonal\nmoments as feature descriptors has been discussed here. Experimental results show that the performance of the\nsystem is dependent on the moment order as well as the type of moments. The orthogonal property of these\nmoments is able to characterize independent features of the palmprint image and thus have minimum\ninformation redundancy in a moment set. Pseudo Zernike moments of order of 15 has the best performance\namong all the moments. Its verification rate is 95.75%, which also represents the overall performance of this\npalmprint verification system.