Expression recognition and synthesis for face-to-face communication

Muscle based face image synthesis[1][2] is one of the most realistic approach to realize interface agent. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces affecting facial tisssue element are calculated by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. In this paper, we introduce the facial muscle model and the strategy of automatic estimation of facial muscle parameters from 2-D marker movements.