Illumination Normalization Based on Local Binary Pattern Image

This paper presents a novel and efficient illumination normalization method based on the local binary pattern Image (LBPI). LBPI is a global description combined by the descriptions of every points in the face image using the local binary pattern (LBP) Compared with the traditional approaches, the experimental results show that our algorithms can significantly improve the performance of face recognition under varying illumination conditions on Yale Face database B.