Facial Expression Feature Extraction Based on Integral Image

Abstract

Expression recognition is an important research direction of pattern recognition, and the facial feature extraction is a key step. This paper presented a simple and fast feature extraction method. In this paper, facial feature points were calculated using integral image and rectangle templates and its results were the feature value, finally these feature value were used for expression classification. The experimental results show that this method improves efficiency while extracting facial feature and does not affect the result heavily.