作者: Jianping Gou , Jun Song , Weihua Ou , Shaoning Zeng , Yunhao Yuan
DOI: 10.1016/J.COMPELECENG.2019.106451
关键词:
摘要: Abstract Representation-based classification (RBC) methods have recently been the promising pattern recognition technologies for object recognition. The representation coefficients of RBC as linear reconstruction measure (LRM) can be well used classifying objects. In this article, we propose two enhanced measure-based based on sparsity-augmented collaborative representation-based method (SA-CRC). One is weighted enhancement (WELRMC) that introduces data localities into SA-CRC. Another two-phase (TPWELRMC) integrates both coarse and fine representations To demonstrate effectiveness proposed methods, experiments are conducted several public face databases in comparison with state-of-the-art methods. experimental results show significantly outperform competing