Automated Face Analysis by Feature Point Tracking Has High Concurrent Validity With Manual FACS Coding

This chapter presents a study that implemented the first version of an automated method of face analysis and assessed its concurrent validity with manual Facial Action Coding System (FACS) coding. Discriminant function analyses are performed on the feature point measurements for action units in brow, eye, and mouth regions. The automated face analysis by feature point tracking demonstrated high concurrent validity with manual FACS coding. The work regarding the behavioral and computer scientists is presented in order to develop and apply a computer-vision-based approach, the CMU/Pitt Automated Facial Image Analysis (AFA) System, to these aspects of facial expression. A summary of the progress with AFA in the recognition and analysis of facial action units and emergent applications to problems in emotion theory and clinical practice is also given.