The objective of the 3-years FASE project, sponsored by STW, started in spring 1997, is to develop a system which can recognize facial movements of a user in front of a camera and use the data thus produced to animate models of the human face. The possible application areas include videophoning and videoconferencing, virtual reality and synthesized actors, animation industry, facial surgical planning and simulation, social user interfaces, lip synchronisation and lip reading for deaf.

The project is a joint effort by two groups, one at the TUD and one at CWI. A detailed description of the entire project might still be found at the FASE project home page.

Here we introduce the research done at CWI. For a quick impression, have a look at the architecture of the system components.

We allow two kinds of facial models:

• 3D physically based ones, aiming at realism.
• 2D drawings, aiming at chartoon-like effects, stylized avatar faces or possibly also animation of 2D photographs of a real face.

A focal point of this project is the creation of editing tools by which one can manipulate the animation data (coming from the recognition module or otherwise.

After having implemented the basic tools, currently we are concentrating on:

• gathering performer data to distillate generic and person-dependent characteristics of certain facial expressions (smile);
• to fine-tune the muscle model, add features to and improve performance of the physically-based model;
• to develop an interactive confirmation tool;
• to extend the animation editing tool with mechanisms to allow the definition and dynamic use of animations as building blocks, synchronisation and other constraints;
• to try out the existing tools in different applications.

For this project contact: Han Noot or Zsófia Ruttkay.

For a totally redesigned commercial version of CharToon, contact Paul ten Hagen at Epictoid for further information.