A proposal for high compression of faces in video sequences using adaptive eigenspaces

The paper presents a proposal for a novel video coding scheme intended to encode human faces in video sequences at very high compression using a recognition and reconstruction approach. The scheme is based on the well-known eigenspace concepts used in face recognition systems, which have been modified to cope with the video compression application. An adaptive mechanism is presented to update the eigenspace which improves the overall approach. The presented first results look promising.