Automatic location of face salient points is one of the key steps in 3D face recognition. This paper presents a fully automatic locating algorithm for 3D facial nose tip and inner eye corner in different views, which relies on a statistical model by combining local shape map and local shape index with the statistical radius of the local shape map. The experimental results on the CASIA 3D face database demonstrate that this method finds more precise location than heuristic algorithms and curvature-based methods.