Animating facial expressions

Abstract

Recognition and simulation of actions performable on rigidly-Jointed actors such as human bodies have been the subject of our research for some time. One part of an ongoing effort towards a total human movement simulator is to develop a system to perform the actions of American Sign Language (ASL). However, one of the "channels" of ASL communication, the face, presents problems which are not well handled by a rigid model.An integrated system for an internal representation and simulation of the face is presented, along with a proposed image analysis model.Results from an implementation of the internal model and simulation modules are presented, as well as comments on the future of computer controlled recognition of facial actions.We conclude with a discussion on extensions of the system, covering relations between flexlble masses and rigid (Jointed) ones. Applications of this theory into constrained actions, such as across rigid nonmovlng sheets of bone (forehead, eyes) are also discussed.

Multimodality in Language and Speech Systems

“…Platt & Badler ( 1981 ), Waters (1987) and Terzopoulos & Waters (1990) have all developed models that simulate the muscles and tensions in the facial tissue. Such models can provide realistic results, but determining proper muscle activation levels required to create a specific facial expression can be a difficult matter, since real muscles do not lend themselves to easy measurement.…”

Abstract muscle action procedures for human face animation

“…Pearce et al (1986) introduced a small set of keywords to extend the Parke model. Platt and Badler (1981) have designed a model that is based on underlying facial structure. Points are simulated in the skin, the muscles and the bones by a set of three-dimensional networks.…”

Expression-Invariant Face Recognition with Expression Classification

“…For example, [15] uses a 3D mask to register the frontal view with the profile view. Some existing masks, such as [16], are well designed for fitting deformable surface according to muscle actions. However, when working with planar face images, it is hard to achieve a good registration for all the densely placed vertexes.…”

“…However, when working with planar face images, it is hard to achieve a good registration for all the densely placed vertexes. Besides, although quad-based masks [16] make morphing flexible, triangulated masks are advantageous in texture mapping. Consequently, we use a simplified and trianglated mask, as shown in Fig.…”