얼굴영상의 분석과 합성에 관한 연구

A Study on the Analysis and Synthesis of Facial Im age

This paper describes a computer vision system for observing the action units of a face using video sequences as input. The visual observationCsensing) is archieved by using an optimal estimation optical flow method coupled with a geometric and a physical (muscle) model describing the facial structure. This modeling results in a time ᅳ varying spatial patterning of facial shape and a parametric representation of the independent muscle action groups, responsible for the observed facial motions. These muscle action patterns may then by used for analysis, interpretation, and synthesis. Thus, by interpreting facial motions within a physics—based optimal estimation framework, a new control model of facial movement is developed.