论文部分内容阅读
Mining and exploring novel discriminating information to boost the performance of the face recognition system is one of the current endeavored directions for face recognition.This paper explores the similarity information of faces belonging to different individuals and proposes a face recognition method based on sparse similarity sequence.Firstly,the concept of similarity sequence is defined to extract the similarity information of faces belonging to different individuals.Next,discriminating information is selected from the similarity sequence through Lasso sparse method.Further,a discrimination criterion is proposed to optimize the sparse degree of the sparse similarity sequence.Finally,the face recognition method is realized based on the optimal sparse similarity sequence.The EER of the proposed method reaches 0.05%and 0.01%respectively on two public face databases-the FacePix database and the FaceMLA database,showing outstanding advantage on performance.