Convolutional sparse coding for face recognition

Abstract

Face recognition has been an important task in pattern recognition and computer vision. Recently, sparse representation has become a popular data representation method in face recognition field. Convolutional sparse coding, which replaces the linear combination of a set of dictionary atoms with the sum of s series of mapping term convoluted with the dictionary filters, was proposed to improve the application performance of traditional sparse coding. In this paper, we apply this convolutional sparse coding method to do the face recognition. As the trained dictionary filters could capture more discriminative information in the corresponding face images, it could believed that better classification performance can be achieved. Experimental results on the face image database demonstrated the novel convolutional sparse coding algorithm can achieve better recognition rate.