A novel model based and waveform based hybrid coding system aimed at very low bit rate coding of face images in video sequences is presented. The well known Principal Component Analysis (PCA) concept which is widely used for face recognition systems is adopted for model based coding, with modifications to cope with video compression. Model failures and unknown objects are handled by waveform based coding employing conventional prediction/transform block-based coding scheme. The two coding modes are combined under rate-distortion framework, where Lagrangian cost function is used to determine the most efficient prediction for each block. Simulations show that the system can achieve high compression ratios while maintaining the robustness and generality, which indicates its potential use for videophone application.

Date Published: 24 June 2005
PDF: 8 pages
Proc. SPIE 5960, Visual Communications and Image Processing 2005, 59603G (24 June 2005); doi: 10.1117/12.631643

Published in SPIE Proceedings Vol. 5960:
Visual Communications and Image Processing 2005
Shipeng Li; Fernando Pereira; Heung-Yeung Shum; Andrew G. Tescher, Editor(s)