Event Details

Facial expression provides cues about emotion and personality and regulates interpersonal behavior. Human-observer based methods for measuring facial expression are labor intensive, qualitative, and difficult to standardize. To make feasible more rigorous, quantitative measurement of facial expression in diverse applications, our interdisciplinary group of behavioral and computer scientists developed and applied a computer-vision based approach, the CMU/Pitt Automated Facial Image Analysis (AFA) System.  AFA is capable of automatically recognizing facial action units and analyzing their timing in facial behavior. This development has opened new areas of research in clinical, developmental, and emotion science, and already has produced new knowledge about the dynamics of individual and interpersonal behavior.  This talk presents an overview of AFA, what it has revealed about expression dynamics, and how we use it to assess clinical depression and physical pain and investigate real-time transfer of emotion expression in computer-mediated face-to-face interaction using a virtual avatar.