Search Here

Computer-vision systems are better than humans in distinguishing between real and faked expression of pain, according to a new study. 

Researchers said the system can be used to detect deceptive actions in the other realms as well including security, psychopathology, job screening and law.

Around 200 human observers were considered for the study. They were asked to asses the veracity of expressions of pain in video clips which contained individuals displaying real painful expressions and faking painful expressions. 

"Human subjects could not discriminate real from faked expressions of pain more frequently than would be expected by chance," said Mark G. Frank, PhD, professor of communication, University at Buffalo, in the press release. "Even after training, they were accurate only 55 percent of the time. The computer system, however, was accurate 85 percent of the time." 

On the contrary, researchers noted that the computer system "managed to detect distinctive, dynamic features of facial expressions that people missed. Human observers just aren't very good at telling real from faked expressions of pain."

To assess the accuracy of the machine versus human vision, researchers had employed the computer expression recognition toolbox (CERT). CERT is an end-to-end system for fully automated facial expression recognition operating in real time.

"In highly social species such as humans," added Kang Lee, PhD, University at Buffalo in the press release, "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."

The study will be published in the latest issue of Current Biology.