摘要
Face recognition under variable illumination conditions is a challenging task. Numbers of approaches have been developed for solving the illumination problem. In this paper, we summarize and analyze some noteworthy issues in illumination processing for face recognition by reviewing various representative approaches. These issues include a principle that associates various approaches with a commonly used reflectance model and the shared considerations like contribution of basic processing methods, processing domain, feature scale, and a common problem. We also address a more essential question - what to actually normalize. Through the discussion on these issues, we also provide suggestions on potential directions for future research. In addition, we conduct evaluation experiments on 1) contribution of fundamental illumination correction to illumination insensitive face recognition and 2) comparative performance of various approaches. Experimental results show that the approaches with fundamental illumination correction methods are more insensitive to extreme illumination than without them. Tan and Triggs'method (TT) using L1 norm achieves the best results among nine tested approaches.
学科与关键词
- Face Recognition under Variable Illumination by Weighted-Subband Edge EnhancementZhao-Rong, Lai; Dao-Qing, Dai; Chuan-Xian, RenCommunications in Computer and Information Science, Springer Berlin Heidelberg, 324-331, 2012.被引 1
- Scalable illumination robust face identification using harmonic representationCong Xia; Jiansheng Chen; Chang Yang; Jing Wang; Jing Liu; Guangda Su; Gang ZhangOther Conferences, 2013.
- Lighting Coefficients Transfer Based Face Illumination NormalizationYuelong, Li; Li, Meng; Jufu, FengCommunications in Computer and Information Science, Springer Berlin Heidelberg, 268-275, 2012.
