The Open Automation and Control Systems Journal

2015, 7 : 569-579
Published online 2015 June 26. DOI: 10.2174/1874444301507010569
Publisher ID: TOAUTOCJ-7-569

Research on Theory and Method for Facial Expression Recognition System Based on Dynamic Image Sequence

Yang Xinfeng and Jiang Shan
School of Computer & Information Engineering, Nanyang Institute of Technology, Henan, 473004, P.R. China.

ABSTRACT

We studied the tracking theory based on Candide3 facial model and according to the research we further developed the tracking process. Based on the research of facial tracking, we put forward a dynamic feature extraction method based on six parameters of facial model. We introduced the active appearance model algorithm to locate and track feature points of facial expression, then studied the tracking theory. Based on Candide3 facial model and according to the research we further developed the tracking process. We use the Dynamic Time Warping (DTW) technique to align the image sequence, and then extract the feature vector. The results show that the method based on the model parameters has a good classification results when extract dynamic characteristics.

Keywords:

Facial expression recognition, face detection, extraction of dynamic feature, the Dynamic Time Warping technique.