Linear combination of face views for low bit rate face video compression

We present a technique for very low bit rate encoding of faces for videoconferencing applications over the Internet or mobile communication networks. The proposed scheme represents each new face view as a linear combination of three basis face views of the same person. The background area of the target face view is also encoded by the same method using the same basis views as used for the face area. Changes in the eyes and mouth regions are encoded using principal components analysis with three training sets of eyes and mouth images of the same person. The scheme results in a very compact representation of the face video data, and good quality images are reconstructed with an estimated bit rate from 1422 to 1620 bits/frame.