Analysis and synthesis of 3-D face image sequence based onmodel-based image coding scheme with an Internet browser

摘要

In this paper, an efficient analysis method for global headmotion, and a synthesis method of 3-D face scenes using model-basedimage coding techniques on the Internet browser are presented. Byapplying the techniques of model-based image coding in facial imagesequence, human face or anthropomorphic agents can be synthesized withreal facial motion on the internet browser using VRML and/or JAVA. Whiletypical model-based image coding produces synthetic face scenes in 2-Dspace at the receiver terminals, the proposed scheme can producesynthetic face scenes in 3-D space interactively supporting some visualstandard. This enables users to synthesize 3-D face scenes at anyterminals. In this sense, it improves the portability of synthesis inmodel-based image coding. To speed up the computation in the analysisprocess, a new method that generates referential frame dynamically isproposed. To produce a 3-D face model which is suitable for the purposeof application, an idea of automatic face modeling using different 3-Dface models is presented. Experimental results show the usefulness ofapplying the techniques of model-based image coding to the analysis offacial motion and synthesis of 3-D face scene on the internet browser