Example-based shape from shading: 3D heads form 2D face images

Images taken of human faces vary in perspective depending on the view-point of the observer. Few of the face recognition methods reported in the literature are capable of recognizing faces under varying pose. To improve the ability of face recognition systems to recognize faces under varying pose, a novel method is proposed in this paper that takes a face image of arbitrary pose and synthesizes a standard frontal-pose image of the same face.