Synthesizing realistic facial animations using energy minimization for model-based coding

Accurate localization and tracking of facial features are crucial for devel oping high-quality model-based coding systems. In this paper we describe th e integration of simple heuristics which are effective in improving the res ults of well-known facial feature detection with robust techniques for adap ting a dynamic mesh for animation. A new method of generating a self-adapti ve mesh using an extended dynamic mesh (EDM) is proposed to overcome the co nvergence problem of the dynamic-motion-equation method (DMM). The new meth od consisting of two-step mesh adaptation (called coarse-to-fine adaptation ) can enhance the stability of the DMM and improve the performance of the a daptive process. The accuracy of the proposed approach is demonstrated by e xperiments on eye model animation. In this paper, we focus our discussion o nly on the detection, tracking, modeling and animation of eye movements. (C ) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd, All rights reserved.