Eigen-Harmonics Faces: Face Recognition under Generic Lighting

Laiyun Qing, Shiguang Shan, Wen Gao

Abstract: The performances of face recognition systems are heavily subject to the variations in lighting. We propose a novel approach for face recognition under generic illumination conditions, named as Eigen-harmonics faces in this work. First, using bootstrap set consisting of 3D face models with texture, we render the spherical harmonic images for every face and train the PCA harmonics faces model. During registration, given a novel face image under arbitrary illumination, we estimate the lighting of the image and recover the PCA coefficients of the spherical harmonics images for this face. During testing, we recognize the face using the PCA coefficients. The experimental results on the images under a wide range of illumination conditions in the public CMU-PIE database are promising.