Facial features motion analysis for wire-frame tracking in model-based moving image coding

This paper addresses the problem of wire-frame tracking by accurate analysis of the motion and the shape of the facial features in head-and-shoulders scenes. Accurate wire-frame tracking is of paramount importance for correct reconstruction of the encoded image, especially in the areas occupied by the lips and the eyes. An entirely new algorithm for tracking the motion of a semantic wire-frame (Candide) by analysis of the principal components of sub-images containing important facial features of the speaker's face is proposed. This algorithm is suitable for tracking both global motion (motion of the speaker's head) and local motion (motion of the facial features). The algorithm was tested on numerous head-and-shoulders sequences with excellent results.