Facial expression provides cues about emotion, regulates interpersonal behavior, and communicates psychopathology. Human-observer based methods for measuring facial expression are labor intensive, qualitative, and difficult to standardize across laboratories, clinical settings, and over time. To make feasible more rigorous, quantitative measurement of facial expression in diverse applications, computer and behavioral scientists at Carnegie Mellon University and the University of Pittsburgh formed an interdisciplinary research team. The team has developed the CMU/Pitt Automated Facial Image Analysis (AFA) system that is capable of automatically recognizing facial action units, analyzing their timing in facial behavior, and rendering real-time photorealistic avatars.
Current efforts use AFA to enable reliable, valid, and efficient measurement of emotion expression, assess symptom severity in depression and physical pain, and investigate human social dynamics. To meet these goals, we pursue basic research to further improve algorithms and capabilities of the AFA system.