Reconstruction of local features for facial video compression

We suggest a feature based facial image reconstruction technique. The encoding technique utilizes the affine structure of the face to capture the global facial motion. The structure information is transmitted only once at the bootstrapping stage. After that only the motion information for each frame is used to reconstruct the image at the decoder. An attempt is made to perform local reconstruction without any colour patching. For local reconstruction lips are tracked across frames using the snake model. An online database of facial features is created from distinct feature templates. The lip feature in each frame is locally reconstructed from existing templates using local warping. The eye templates for each frame are also recognized and pasted from the online database.