标题：Illumination Invariance Face Recognition Using Wavelet Coefficients and Local Binary Pattern
作者：Lu, Hua; Yang, Ming-qiang; Ben, Xian-ye
作者机构：[Lu, Hua; Yang, Ming-qiang; Ben, Xian-ye] Shandong Univ, Sch Informat Sci & Engn, Jinan 250100, Peoples R China.
会议名称：International Conference on Artificial Intelligence and Software Engineering (AISE)
会议日期：JAN 11-12, 2014
来源：INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND SOFTWARE ENGINEERING (AISE 2014)
关键词：Wavelet transform; Illumination variations; Local binary pattern
摘要：This paper presents a novel method for face recognition under different illumination conditions. In the proposed approach, firstly, image is pre-processed to extract an approximation sub-band and several detail sub-bands which are robust to illumination variation using Wavelet Transform in the logarithm domain, and then directly discards almost all low frequency information to decrease the influence of the illumination. Secondly, Local Binary Pattern(LBP) is used to decrease the noise and extract the face feature. Finally, the result can be obtained by Support Vector Machine Classifiers. The proposed method is tested on CMU-PIE and Yale B face database, and high recognition rate prove that proposed method is robust to varying lighting conditions.