Principal Component Analysis based Palmprint Recognition with Center of Mass Moments
M. Madheswaran · 2012
Palmprint is one of the relatively new physiological biometrics due to its stable and unique characteristics. The rich feature information of palm print offers one of the powerful means in personal recognition. Palmprint Region Of Interest (ROI) segmentation and feature extraction are two important issues in palmprint recognition. This paper introduces two steps center of mass moment method for ROI segmentation and Principal Component Analysis (PCA) for obtaining palmprint feature vector and matching is done by Hausdroff Distance method(HD). The recognition rates are unexpectedly improved compared to the classic approach. Experiment results show that this system can achieve a high performance.