Enhanced Gabor-based region covariance matrices for palmprint recognition

Abstract

An enhanced Gabor-based region covariance matrices (EGRCM) method for palmprint recognition is proposed. Motivated by the fact that both the Gabor magnitude (GM) and the Gabor phase (GP) of a certain image contain effective information for image feature extraction, they are utilised simultaneously to construct the proposed EGRCM image descriptor for palmprint recognition. Experimental results demonstrate the efficacy of the proposed method.