3D Facial Lip-motion Synthesis

In this thesis, the lip-motion driven by text or actions respectively, and the designand implementation of the interactive human face editor are all discussed andlucubrated.By investigating the pronunciation rules of the Chinese Phonetic Word, I use sevenlip-shapes of viseme and their time proportion to drive the 3D facial model toimplement lip-motion.In the lip motion driven by action aspect, I use Kriging Estimator to control the lipmodel morphing result. According to the position of lip feature points extracted fromvideo images, the lip model can be driven with Kriging method.I build an interactive human face editing and synthesis system, which can not onlyinteractively edit individual human face but also real-time display 3D lip animation with30 frame per second. No matter now or in the future, the technique and algorithmaccomplished in this paper will play an important role in many aspects such ascommunication, education and entertainment.