Abstract
As a reliable biometric characteristic, the palmprint recognition has recently represented an emerging trend in the pattern recognition field. It is a human physiological feature that ensures the identification of one person from another. In this paper we present a novel approach which is based on three main proposed steps of the palmprint recognition system. First, we propose a reliable algorithm to locate the Regions Of Interest (ROI) of the hand. This algorithm is able to classify the hand into left hand or right hand. Second, we extract the texture features descriptors of this resulting ROI palmprint location using the gray-level co-occurrence matrix (GLCM) method which is based on the local Haralick features. This method has been broadly applied in many fields, particularly in the domain of image processing for analyzing the image texture. Finally, we classify these extracted features by the use of the SVM method in order to make a decision and to attain a high recognition rate. The performance of the presented approach was assessed experimentally on two largely database called "CASIA-Palmprint" and "PolyU-2D-3D-palmprint". The experimental results of this evaluation show promising results and demonstrate the effectiveness of the proposed approach. The results obtained are compared to others well-known state of the arts techniques.