ance model in the framework. We have focused on the problem of how to make
the appearance model more flexible so that it can be used in various conditions.
For this purpose, we have developed efficient methods for modeling the illu-
mination effects and reduce the person-dependency of the appearance model.
To evaluate face motion analysis, we have done facial expression recognition
experiments to show that the flexible appearance model improve the results
under varying conditions. We shall also present synthesis examples using the
flexible appearance model.
A unified 3D face processing framework.
2.2 3D face geometry modeling
Generating 3D human face models has been a persistent challenge in both
computer vision and computer graphics. A 3D face model lays basis for model-
based face video analysis and facial animations. In face video analysis, a 3D
face model helps recognition of oblique views of faces [Blanz et al., 2002].
Based on the 3D geometric model of faces, facial deformation models can be
constructed for 3D non-rigid face tracking [DeCarlo, 1998, Tao, 1999]. In
computer graphics, 3D face models can be deformed to produce animations.