3D face recognition by SURF operator based on depth image

Expression variation is one of the most important factors that considerably influence the performance of face recognition. In order to enhance robustness to expression variations, a procedure of 3D face recognition based on depth image and SURF Operator is proposed. We use Fisher Linear Discriminant (FLD) method on the depth image to perform coarse recognition first to catch the highly ranked 3D faces. This stage can distinguish those faces that differ significantly and it is robust to expression variations to some extent. On the basis of this step, we extract the SURF features of the 2D gray images, that are corresponding only to those highly ranked 3D faces, to carry out the refined recognition. The experiments indicated a high recognition rate by our procedure even when the face expressions of training samples differ greatly from testing samples.