Automatic Facial Image AnalysisJ.F. CohnDivision of Psychology, University of Pittsburgh, Pittsburgh, PA, USA and the Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USAFacial expression is one of the most powerful, natural, and immediate means for human beings to communicate their emotions and intentions. The face can express emotion sooner than people verbalize or even realize their feelings. To make optimal use of the information afforded by facial expression, reliable, valid and efficient methods of measurement are critical. Two major advances toward this goal were the human-observer-based Facial Action Coding System (FACS) and facial electromyography (EMG). The third major advance - automatic facial image analysis - combines the best features of FACS and EMG: Comprehensive description of facial expression (FACS) and quantitative, automatic measurement, which was previously possible only by using invasive facial sensors (EMG). This talk reviews previous approaches to facial measurement (FACS and
facial EMG) and the advances in automatic facial image analysis they inform.
It reviews technical and conceptual challenges that lay ahead and the
approaches of leading investigators. It describes capabilities and limitations
of current systems, applications in emotion and social interaction, and
what we have already learned using these new systems about the configuration
and timing of facial expression. Paper presented at Measuring Behavior 2005 , 5th International Conference on Methods and Techniques in Behavioral Research, 30 August - 2 September 2005, Wageningen, The Netherlands. © 2005 Noldus Information Technology bv |