Noise versus Facial Expression on 3D Face Recognition

This paper presents a new method for 3D face recognition. The method combines a Simulated Annealing-based approach for image registration using the surface interpenetration measure (SIM) to perform a precise matching between two face images. The recognition score is obtained by combining the SIM scores of four different face regions after their alignment. Experiments were conducted on two databases with a variety official expressions. The images from the databases were classified according to noise level and facial expression, allowing the analysis of each particular effect on 3D face recognition. The method allows a verification rate of 99.9%, at a false acceptance rate (FAR) of 0%, for the FRGC ver 2.0 database when only noiseless, neutral expression face images are used. Also, the results using face images with expressions and noise demonstrate that subjects still can be recognized with 87.5% of verification rate, at a FAR of 0%.