Using Geodesic Distances for 2D-3D and 3D-3D Face Recognition

In this paper, we propose an original framework for rep- resenting 2D and 3D face information using geodesic dis- tances. This aims to define a representation enabling 3D- 3D face recognition as well as the direct comparison be- tween 2D face images of a subject against its 3D face model. This representation is extracted by measuring geodesic dis- tances in 3D and 2D. In 3D, the geodesic distance between two points on a surface is computed as the length of the shortest path connecting the two points. In 2D, the geo- desic distance between two pixels is computed based on the differences of gray level intensities along the segment con- necting the two pixels. Experimental results are reported for 3D-3D and 2D-3D face recognition, in order to demon- strate the potential of the proposed solution.