Abstract:
In this paper, we introduce a new system for
3D face recognition. We are making use of 48 small
regions on the face that allow for the highest level of 3D
face recognition. We are translating the incoming image
to the origin and crop 48 regions, which is defined by
cuboids of appropriate radius centered at the nose tip.
We are making use of regions that are consistent in the
presence of facial expressions. Our algorithm reduces
the effects caused by variation in expression . We are
comparing and analyzing the performance based on 38
regions and 48 regions.
