ENCODING AND DECODING OF FACE BASED ON MODEL USED CHARACTERISTIC DETECTION AND ENCODING OF INHERENT FACE

摘要

PROBLEM TO BE SOLVED: To provide a method for sending an image of a face with high condensation in a video telephone conference. SOLUTION: This method uses a three-dimensional face model and a method that is called decomposition of an inherent face, and one terminal 11 analyzes video. In such cases, encoding of the position of a face characteristic and the inherent face of a face image is sent to an decoder 13. The decoder 13 synthesizes the face images with a receiving terminal. A three-dimensional model that is arranged according to a detected characteristic position is made into a texture map by using decoding of the inherent face.