Analysis and Synthesis of Facial Expressions

In this chapter, the state-of-the-art in facial animation and expression analysis is reviewed and new techniques for the estimation of 3-D human motion, deformation, and facial expressions from monocular video sequences are presented. Since illumination has a considerable influence on the appearance of objects in a scene, methods for the derivation of photometric scene properties from images are also addressed. For a particular implementation, the potential of these analysis techniques is illustrated for applications like character animation and model-based video coding. Experiments have shown that the usage of 3-D computer models allows video transmissions at bit-rates of a few kbit/s, enabling a wide variety of new applications.Request access from your librarian to read this chapter's full text.