Using skin-color motion for 3D face modelling and synthesis

Abstract

Today 3D human face models have been widely used in applications such as face recognition, head tracking, facial expression recognition, human action recognition, video compression/coding and facial animation. Modeling human faces provides a potential solution to identifying faces with variations in illumination, pose, and facial expression. We propose a method of modeling human faces based on a generic MPEG-4 face model (a triangular mesh model) and individual facial characteristics containing both shape and texture information. The modeling method adapts a generic face model to the extracted facial features.