Citation

Goh, Michael Kah Ong and Teoh, Andrew Beng Jin and Tee, Connie (2010) Bimodal palm print and knuckle print recognition system. Journal of IT in Asia 3. pp. 53-56.

Text 9.pdf Restricted to Repository staff only Download (1MB)

Abstract

This paper proposed an innovative contact - less palm print and knuckle print recognition system. Palm print is referred to as line textures, which contains principal lines, wrinkles and ridges on the inner surface of the palm. On the other hand, knuckle print is denoted as the flexion lines on the inner skin of the knuckles of the fingers. These line patterns are unique and stable, and they offer abundance of useful information for personal recognition. We present a novel palm print and knuckle print tracking approach to automatically detect and capture these features from low resolution video stream. No constraint is imposed and the subject can place his/her hand naturally on top of the input sensor without touching any device. The palm print and knuckle print features are extracted using our proposed Wavelet Gabor Competitive Code and Ridget Transform methods. Several decision - level fusion rules are used to consolidate the scores output by the palm print and knuckle print experts. The fusion of these features yields promising result of EER=1.25% for verification rate.

Item Type:	Article
Subjects:	Q Science > Q Science (General)
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	30 Dec 2013 02:11
Last Modified:	30 Dec 2013 02:11
URII:	http://shdl.mmu.edu.my/id/eprint/4682

Downloads

Edit (login required)