An Illumination Processing Algorithm Based on Total Variation Model
Liansheng Zhuang, X Ye, Yong Wang, Zhenquan Zhuang, Bin Li · 2006
A processing algorithm was presented for face recognition under variation illumination. It needs only one parameter to set and can remove the "halo" efficiently. Firstly, it estimated the illumination from image using total variation model. Secondly, it recovered the image reflectance, which is invariant of illumination. Experiment results show that this algorithm can improve the face recognition rate under varying lighting conditions