Automatic analysis and recognition of brow actions and head motion in spontaneous facial behavior

Abstract

Previous efforts in automatic facial expression recognition have been limited to posed facial behavior under well-controlled conditions (e.g., frontal pose and minimal out-of-plane head motion). The CMU/Pitt automated facial image analysis system (AFA) accommodates varied pose, moderate out-of-plane head motion, and occlusion. AFA was tested in video of two-person interviews originally collected to answer substantive questions in psychology, and represent a substantial challenge to automatic recognition of facial expression. This report focuses on two action units, brow raising and brow lowering because of their importance to emotion expression and paralinguistic communication. For two-state recognition, AFA achieved 89% accuracy. For three-state recognition (brow raising, brow lowering, and no brow action), accuracy was 76%. Brow and head motion were temporally coordinated. These findings demonstrate the feasibility of action unit recognition in spontaneous facial behavior.