The computer expression recognition toolbox (CERT)

TLDR

The authors introduce CERT, a free academic software toolbox for fully automatic real‑time facial expression recognition. CERT automatically codes 19 FACS action intensities and 6 prototypical expressions, estimates 10 facial feature locations and 3‑D head orientation. On CK+ CERT achieves 90.1 % accuracy on action coding, nearly 80 % on spontaneous expressions, and processes 320 × 240 video at ~10 fps in real time.

Abstract

We present the Computer Expression Recognition Toolbox (CERT), a software tool for fully automatic real-time facial expression recognition, and officially release it for free academic use. CERT can automatically code the intensity of 19 different facial actions from the Facial Action Unit Coding System (FACS) and 6 different prototypical facial expressions. It also estimates the locations of 10 facial features as well as the 3-D orientation (yaw, pitch, roll) of the head. On a database of posed facial expressions, Extended Cohn-Kanade (CK+[1]), CERT achieves an average recognition performance (probability of correctness on a two-alternative forced choice (2AFC) task between one positive and one negative example) of 90.1% when analyzing facial actions. On a spontaneous facial expression dataset, CERT achieves an accuracy of nearly 80%. In a standard dual core laptop, CERT can process 320 × 240 video images in real time at approximately 10 frames per second.