IVML  
  about | r&d | publications | courses | people | links
   

F. Piat and N. Tsapatsoulis
Exploring the Time Course of Facial Expressions with a Fuzzy System
IEEE International Conference on Multimedia and Expo, New York City, NY, July 2000
ABSTRACT
Recognizing facial expressions is one of the important challenges of current research in Human-Computer Interaction (HCI). Previous research show the limits of recognition based on a single static image, and analyzing video sequences seems more promising. We explore here three fuzzy systems for the classification of basic facial expressions and compare their performances with a template-correlation approach. We then use those to examine the time course dynamics of facial expressions. The system's inputs are the relative variations of distances defined by salient facial points from one frame to the next. For maximum compatibility, those facial points (eyebrows, eyes, mouth) were chosen from the set of points defined in the standard MPEG-4 specifications, and so that their automatic extraction is tractable. The first results suggest that some expressions can be recognized early after the onset. For other expressions, it is in general possible to reduce significantly the number of possibilities. Forming early hypotheses regarding the expression could be necessary for a system to work in real-time, since other steps may have to follow: prediction of user's action, choice of computer's action, etc. This also has implications for the recognition of milder expressions.
30 July , 2000
F. Piat and N. Tsapatsoulis, "Exploring the Time Course of Facial Expressions with a Fuzzy System", IEEE International Conference on Multimedia and Expo, New York City, NY, July 2000
[ BibTex] [ Print] [ Back]

© 00 The Image, Video and Multimedia Systems Laboratory - v1.12