Skip to Main Content
Adaptive smoothing for face image normalisation under variation of illumination is presented. The illumination is estimated by iteratively convolving the input image with a 3-by-3 averaging kernel weighted by a simple measure of the illumination discontinuity at each pixel. In particular, weights of a kernel are encoded into a local binary pattern (LBP) to achieve fast and memory efficient processing. In the framework of the retinex based method the proposed method gives superior experimental results.
Date of Publication: Nov. 22 2007