Blockwise collaborative representation-based classification via L2-norm of query data for accurate face recognition

A new blockwise collaborative representation-based classification with L2-norm of test data for accurate face recognition is presented. For training we divide images into several blocks and estimate representation coefficients of each block via L2-norm minimisation. For testing, the L2-norm of test image blocks are scaled by the trained representation coefficients. A novel classification scheme based on the L2-norm of test blocks is proposed and this scheme is jointly applied with conventional reconstruction error-based classification. Experimental results show that the proposed methods outperform other representation-based methods for face recognition.