High Performance Palmprint Identification System Based On Two Dimensional Gabor

Palmprint is a relatively new in physiological biometrics. Palmprint region of interest (ROI) segmentation and feature extraction are two important issues in palmprint recognition. The main problem in palmprint recognition system is how to extract the region of interest (ROI) and the features of palmprint. This paper introduces two steps in center of mass moment method for ROI segmentation and then applied the Gabor two dimensional (2D) filters to obtain palm code as palmprint feature vector. Normalized Hamming distance is used to measure the similarity degrees of two feature vectors of palmprint. The system has been tested by using database 1000 palmprint images, are generated from 5 samples from each of the 200 persons randomly selected. Experiment results show that this system can achieve a high performance with success rate about 98.7% (FRR=1.1667%, FAR=0.1111%, T=0.376).