Personal Identification System based on Multiple Palmprint Features

Abstract

This paper presents a palmprint recognition system with palmprint images collected by a high-resolution color scanner. The scanned RGB image of the palmprint is pre-processed and the region of interest (ROI) of the palm is determined by the finger gap locations. Three sets of features extracted from the ROI image by the 2D Gabor filter using the palmprint phase orientation code (PPOC) represent texture information of the palm in the form of a real component, an imaginary component and an orientation component, respectively. The recognition is performed by applying the enhanced linear discriminant analysis (EDLDA) coupled with the nearest neighbor classifier on these three feature sets, respectively, and the decisions are combined via the majority voting scheme to yield the ultimate recognition. Experiments on our collected palmprint image database show promising recognition rate of 99.6% with a low False Acceptance Rate (FAR) of 0.02%