VASC Seminar Announcement ========================= Date: Monday, 2/7/00 Time: 3:45-4:45 Place: NSH 3002 Speaker: Yingli Tian CMU Robotics Institute http://www.ri.cmu.edu/people/tian_ying_li.html Title: Recognizing Action Units for Facial Expression Analysis Abstract: I will present the new results of the automated facial expression analysis project. Facial analysis has received a lot of attention in the human face detection, recognition and man-machine interface literature since the early 1970's. Facial expressions provide sensitive cues about emotional responses and play a major role in the study of psychological phenomena and the development of nonverbal communication. Most facial expression recognition systems focus on only six basic expressions. However, in everyday life, emotion or intent is more often communicated by subtle changes in one or two discrete features. Humans are capable of producing thousands of expressions that vary in complexity, intensity, and meaning. The objective of this project is to develop a computer vision system, including both facial feature extraction and recognition, that automatically discriminates among subtly different facial expressions based on Facial Action Coding System (FACS) action units (Aus). For recognizing subtle changes of expression, the detail facial features must be extracted accurately and robustly. It must cope with the large variation in appearance across subjects and the combination of rigid and non-rigid motion. In this talk, I will introduce a work toward a robust system to detect and track facial features including lip, eyes, eyebrows, cheek, and furrows by using multi-state face and facial component models by combining color, shape, edge and motion information. The lip and eye contours can be recovered from the tightly closed mouth (all lips disappeared) and the closed eye. Then, I will present the features representation for facial expression analysis and conclude with a discussion of results from the face Action Units recognition by neural network.