A computer system is better at differentiating between real and fake pain than humans, according to a new study.
The latest system can be used in detecting deception, researchers said.
The study, conducted by researchers at University of California, San Diego, and the University of Toronto, found that the ability of most people to spot fake pain expressions was no better than a random chance. Even after training, people caught the false expression with an accuracy of just 55. A computer system can tell whether or not a person is faking it with 85 percent accuracy.
"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, according to a news release. "Human observers just aren't very good at telling real from faked expressions of pain."
The computer-visual system- apart from being used by the Big Brother - could also be used in homeland security, medicine and law.
But, why are humans so bad at spotting a fake pain expression? After all, a computer system just follows a set of commands while a human brain has an intricate network of neurons processing several bits of data at once.
It turns out that the highly-evolved brain actually prevents people from detecting the fake 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 Kang Lee at the University of Toronto, senior author of the study.
How can you spot a fake expression? According to the researchers, the mouth was "the single most predictive feature of falsified expressions." People who fake a pain expression open their mouths regularly and with fewer variations.
The study is published in the journal Current Biology.