Vision-based animation of 3D facial avatars

We propose a system that classifies a user´s facial expressions captured by a webcam and applies notable characteristics of the classified expression to an animated 3D facial avatar. The facial avatar is composed of multiple 3D models where a face model is combined with accessorial models such as facial hair. Such accessorial models are used to decorate the avatar, and are automatically registered with the face model during animation. Our system classifies facial expressions in real time by incorporating Active Shape Models and Support Vector Machines. Users can easily control the facial animation of avatars by just expressing their emotion in front of a webcam.