Abstract
We describe an approach to synthesizing human expressions based on 3D face model and the facial motion parameters obtained by tracking the model vertices in real expression sequences. The synthetic sequences of different expressions can be generated by deforming the face model using these motion parameters. This method can be used to effectively compress video sequences where the human faces are dominant, such as video phones and teleconferences.
| Original language | English (US) |
|---|---|
| Article number | 413880 |
| Pages (from-to) | 98-102 |
| Number of pages | 5 |
| Journal | Proceedings - International Conference on Image Processing, ICIP |
| Volume | 3 |
| DOIs | |
| State | Published - 1994 |
| Event | The 1994 1st IEEE International Conference on Image Processing - Austin, TX, USA Duration: Nov 13 1994 → Nov 16 1994 |
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Signal Processing