A Novel Clustering-Based Feature Extraction Method for an Automatic Facial Expression Analysis System

Facial expressions are the facial changes in response to a person´s internal emotional states, intentions or social communications. In this paper, we fulfill the recognition of facial action units, i.e., the subtle change of facial expressions, and emotion-specified expressions. Our automatic facial expression analysis system includes face detection, facial component extraction, tracking and representation, and facial expression recognition. The optimum facial feature extraction algorithm, Canny Edge Detector, is applied to localized face images, and a hierarchical clustering-based scheme reinforces the search region of extracted highly textured facial clusters. Ultimately, the processed feature vector is passed to trained pattern classifiers to distinguish different facial expressions/emotions. Experimental results show that our proposed Automatic Facial Expression Analysis system can be well applied to real-time facial expression and emotion categorization tasks.