1989 年 13 巻 56 号 p. 89-96
This paper presents a facial feature. information extraction and face reproduction method for the Virtual Space Teleconferencing System, and Shows the experiment results. In this System, there is a need to generate three-dimensional facial models from facial images and to synthesize images of the models virtually viewed from different angles. Feature points are extracted from front and Side views of the face with profile features and information about the position and correlation of the feature points. The system synthesizes images after modifying a face model with three-dimensional data from the extracted feature points. In this method, it is possible to generate a face model Without a human operator as in other conventional face modeling techniques.