1 Automated Face Analysis for Affective Computing

Facial expression communicates emotion, intention, and physical state, and regulates interpersonal behavior. Automated Face Analysis (AFA) for detection, synthesis, and understanding of facial expression is a vital focus of basic research. While open research questions remain, the field has become sufficiently mature to support initial applications in a variety of areas. We review 1) human-observer based approaches to measurement that inform AFA; 2) advances in face detection and tracking, feature extraction, registration, and supervised learning; and 3) applications in action unit and intensity detection, physical pain, psychological distress and depression, detection of deception, interpersonal coordination, expression transfer, and other applications. We consider user-in-the-loop as well as fully automated systems and discuss open questions in basic and applied research