Intelligent system for automatic adjustment of 3D facial shape model and face expression recognition

Abstract

A facial expression recognition system using features from the automatically adjusted 3D facial shape model is proposed in this dissertation. The region of face is detected from input images with a face and the 3D facial shape model is deformed to fit the detected region and the facial feature points. In this paper, the face synthesis techniques are applied to face region detection and the extracted features are used for training of the intelligent facial expression recognition system. Then the face expression recognition system employs a neuro-fuzzy technology with supervised-learning function. Some experiments are accomplished using various image data, it was turned out that the region detection and 3D shape model adjustment method is efficient and the processing time was reduced.