3D facial range models can be created by static range scanners or real-time dynamic 3D imaging systems. One of the major obstacles for analyzing such data is lack of correspondences of features (or vertices) due to the variable number of vertices across individual models or 3D model sequences. In this paper, we present an effective approach to automatically establish vertex correspondences for feature registration, and further classify facial models to specific expressions. We describe our proposed approach as how to establish correspondences among individual models based on a 2D intermediary, which is generated using a conformal mapping and model adaptation algorithm. We also present our approach for 3D facial expression labeling, registration, tracking, and categorization. The feasibility of the approach is validated and demonstrated using our created 3D facial expression databases.
展开▼
