Consider yourself forewarned. A new study says you can deceive people - but not a computer.
Researchers at the University of California, San Diego and the University of Toronto claimed that a computer system can spot real or fabricated expressions of pain - far more accurately than humans can.
The joint study, titled "Automatic Decoding of Deceptive Pain Expressions," shows that the computer system spotted distinct dynamic features of facial expressions, which may even be missed by people. Two main elements of said system are machine learning and computer vision.
The study also notes an 85-percent accuracy of computers, as opposed to the modest 55-percent accuracy among humans even after much practice and training in detection. The Current Biology published said study.
Marian Bartlett, lead author of the study and research professor at Institute for Neural Computation in UC San Diego, said that people aren't just that good enough at deciphering real from fabricated expressions of pain.
While humans can fake facial expressions, which can well enough mislead most witnesses, the pattern-recognition abilities of a computer can prove far better as to whether the pain is real or faked, Kang Lee said, a senior author of the study.
"Perceptual processes that are very easy for humans are hard for computers," Bartlett said. "This is one of the first examples of computers being better than people at a perceptual process."
Bartlett's team developed the method based on the idea that fake and genuine emotional expressions involve varied pathways in the brain. It also based the method on the Facial Action Coding System (FACS), made popular by psychologist Paul Ekman in 1970s and 1980s. The system boils down to the idea that each movement records onto a particular muscle or even set of muscles.
"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, who is also professor at the Dr. Eric Jackman Institute of Child Study at the University of Toronto.
Researchers disclosed that the way you open your mouth is the most predominant feature if the expression is fake or fabricated. When you fake pain, you tend to open and close your mouth in a regular pattern.
Aside from detecting false pain expressions, the computer-vision system might also be utilized to spot other real-life deceiving actions in important areas.
"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," Bartlett disclosed.
The new study reminds of Google Glass app in beta testing that claims to give real-time information of emotional expressions of people in sight.
