3D face representation using scale and transform invariant features

In this study a representation using scale and invariant generic 3D features, for 3D facial models is proposed. These generic feature vectors obtained from descriptive parts of the face like eyes, nose, or nose saddle, are then convolved into a graphical model where a characteristic topology for a 3D facial model representation is achieved. These scale and invariant 3D features are determined by using the Gaussian (K) and mean (H) curvature values on the facial surface and by examining various scales in the scale space. The curvatures are used to define fundamental elements on the surface such as, pits, peaks and saddles with their scale, normal and orientation information, where they assemble the mentioned generic features.