An efficient method to detect facial fiducial points for face recognition

In this paper, a completely automatic face recognition system is presented. It consists of two main modules: in the first, the facial fiducial points are localized, and in the second, the face is characterized applying a bank of Gabor filters in correspondence to the found fiducial points. This method is an evolution of the one we have presented; the fiducial point estimation is more efficient and self-correcting, and the face characterization is modified.