A Novel Bimodal Identification Approach Based on Hand-Print

Abstract

A new approach for the personal identification using hand images is presented. This paper attempts to improve the performance of palm-print-based verification system by integrating hand geometry features and finger-print features. Unlike other bimodal biometric systems, the users do not have to undergo the inconvenience of using two diferent sensors since the palm-print, finger-print and hand geometry features can be acquired from the same image. Three kinds of handprint features are extracted for the identification. First the hand geometric feature is used for a coarse matching to select the similar candidates from database. Then the finger print and palm print feature are presented by wavelet zero-crossing. After that both of the two kinds of 1-D features are used in the fine level identification stage. The proposed algorithm has been shown to classify hand-prints with an accuracy of 97%.