Computer Systems Identify Fake Expressions of Pain Better Than Humans

Researchers have found that when compared to humans, a computer system can more accurately identify real or fake expressions of pain.

The study, led by researchers at the University of California and University of Toronto, found that humans failed to differentiate real expression of pain from the fake one. Even after training, humans were just 55 percent accurate in discriminating the real from fake expression of pain when compared to the computer system that was 85 percent accurate.

"The computer system managed to detect distinctive dynamic features of facial expressions that people missed," said Marian Bartlett, research professor at UC San Diego's Institute for Neural Computation and lead author of the study. "Human observers just aren't very good at telling real from faked expressions of pain."

According to Senior author Kang Lee, professor at the Dr. Eric Jackman Institute of Child Study at the University of Toronto, most humans can replicate facial expressions as well as fake emotions to deceive observers.  Compared to the humans, the computer's pattern-recognition ability is more accurate in identifying the expressions.

"In highly social species such as humans, faces have evolved to convey rich information, including expressions of emotion and pain. And, because of the way our brains are built, people can simulate emotions they're not actually experiencing - so successfully that they fool other people. The computer is much better at spotting the subtle differences between involuntary and voluntary facial movements," said Lee.

The one predictive feature involved in false expression is the mouth- how and when the person opens the mouth predicts whether or not the pain is real.  If the person is putting up a faked expression of pain, the mouth opens regularly with a very limited variation. 

The researchers further investigated whether extreme regularity in opening mouth is a general feature of a fake expression.

Apart from discriminating between the real and fake pain, computer vision system can also be used in other deceptive actions that include homeland security, job screening, medicine, law and psychopathology.

"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. In addition, our computer-vision system can be applied to detect states in which the human face may provide important clues as to health, physiology, emotion, or thought, such as drivers' expressions of sleepiness, students' expressions of attention and comprehension of lectures, or responses to treatment of affective disorders," said Bartlett.

The finding was documented in Current Biology.