In this paper, a method for low-dimensional illumination space representation (LDISR) of human faces is proposed. The method can not only synthesize a virtual face image when given lighting condition but also estimate lighting conditions when given a face image. The LDISR is based on the observation that 9 basis point light resources can represent almost arbitrary lighting conditions for face recognition application and different human faces have the similar LDISR. The advantage of LDISR is that it can be trained on images of one human face and can be used for all human faces. The experiments on image reconstruction indicated the efficiency of LDISR.
展开▼