Sign In

Communications of the ACM

ACM TechNews

Computers Spot False Faces Better Than People

View as: Print Mobile App Share:
A computer has beaten humans in identifying real vs. fake facial expressions of pain.

Researchers found a computer system more accurate than humans in recognizing real or fake expressions of pain.


A computer system bested humans in recognizing real or fake expressions of pain in a joint study from researchers at the University of California, San Diego (UCSD) and the University of Toronto. The detection rate for humans was not better than random chance, and training only improved accuracy to 55 percent, the researchers say. However, the computer system attained an accuracy level of 85 percent.

The team used a computer-vision system, which could spot the subtle differences between involuntary and voluntary facial movements. "By revealing the dynamics of facial action through machine-vision systems, our approach has the potential to elucidate 'behavioral fingerprints' of the neural-control systems involved in emotional signaling," says lead author and UCSD professor Marian Bartlett.

She says the computer-vision system also could be used to detect driver sleepiness, student comprehension of subject matter, or treatment of affective disorder response. "As with causes of pain, these scenarios also generate strong emotions, along with attempts to minimize, mask, and fake such emotions, which may involve 'dual control' of the face," Bartlett says.

From University of Toronto
View Full Article


Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


No entries found