A Novel Face Recognition Algorithm Based on Improved Retinex and Sparse Representation

Abstract

In recent years, face recognition technology has been widely used as a kind of important modern biological recognition technology. As one of the main factors that affect the recognition rate, the illumination variation has attracted the attention of many researchers. In order to improve the face recognition under illumination variation condition, a novel face recognition algorithm based on improved Retinex and sparse representation is proposed in this paper. Retinex algorithm can be used to solve the problem of face illumination variation in face recognition, but it is easy to produce ‘halo’ phenomenon. In order to improve the face recognition rate under the change of illumination condition. In this paper, firstly, in order to eliminate the interference of illumination on face recognition, we apply the Retinex that is improved by partial differential equations to face image processing. Then, sparse representation is used to extract face feature vector, and the voting method is used to realize the face recognition. Finally, the performance of the algorithm is tested by 3 standard face databases. The results show that the proposed algorithm can improve the face recognition rate under different illumination conditions, and has good robustness to illumination.