Parameterized Models for Facial Animation
IEEE Computer Graphics and Applications
Hi-index | 0.00 |
Facial Features of a videophone image sequence are coded using the traditional technique of Principal Components (PCs). One of the main advantages of this method is that it makes use of a high apriori knowledge of the images as well as exploits the correlation between pixel values. The sequences are coded through a hybrid wire frame model in which the head and shoulder images are coded using a low number of bits. A box is placed around the mouth and eye regions whch are coded at a hgher bit rate using PCs. Since the image sequence is similar in its overall configuration, this scheme gives a very hgh compression ratio of around 500:1.