AUTOMATED CODING OF FACIAL BEHAVIOR IN HUMAN-COMPUTER INTERACTIONS WITH FACS

A method was developed for automated coding of facial behavior in computer-aided test or game situations. Facial behavior is registered automatically with the aid of small plastic dots which are affixed to pre-defined regions of the subject's face. During a task, the subject's face is videotaped, and the picture is digitized. A special pattern-recognition algorithm identifies the dot pattern, and an artificial neural network classifies the dot pattern according to the Facial Action Coding System (FACS; Ekman & Friesen, 1978). The method was tested in coding the posed facial expressions of three subjects, themselves FACS experts. Results show that it is possible to identify and differentiate facial expressions by their corresponding dot patterns. The method is independent of individual differences in physiognomy.