Computers can spot real or fake expressions of pain better than people

May 26, 2014 by Paul Mueller, University of California - San Diego
Computer science Ph.D. alumnus Jacob Whitehill demonstrating real and fake expressions of pain in this picture. While at the Jacobs School, Whitehill led an effort to use automated facial expression recognition to make robots better teachers and turned his face into a remote control in the process.

A joint study by researchers at the University of California San Diego and the University of Toronto has found that a computer system spots real or faked expressions of pain more accurately than people can.

The work, titled "Automatic Decoding of Deceptive Pain Expressions," is published in the March 20 issue of Current Biology.

"The managed to detect distinctive dynamic features of 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 ."

Senior author Kang Lee, professor at the Dr. Eric Jackman Institute of Child Study at the University of Toronto, said "humans can simulate facial expressions and fake emotions well enough to deceive most observers. The computer's pattern-recognition abilities prove better at telling whether pain is real or faked."

The research team found that humans could not discriminate real from faked expressions of pain better than random chance – and, even after training, only improved accuracy to a modest 55 percent. The computer system attains an 85 percent accuracy.

"In highly social species such as humans," said Lee, "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."

"By revealing the dynamics of facial action through machine vision systems," said Bartlett, "our approach has the potential to elucidate 'behavioral fingerprints' of the neural-control systems involved in emotional signaling."

The single most predictive feature of falsified expressions, the study shows, is the mouth, and how and when it opens. Fakers' mouths open with less variation and too regularly.

"Further investigations," said the researchers, "will explore whether over-regularity is a general feature of fake expressions."

In addition to detecting pain malingering, the computer-vision system might be used to detect other real-world deceptive actions in the realms of homeland security, psychopathology, job screening, medicine, and law, said Bartlett.

"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," she said. "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."

Explore further: Determination might be a very human expression

More information: Marian Stewart Bartlett, Gwen C. Littlewort, Mark G. Frank, Kang Lee. "Automatic Decoding of Facial Movements Reveals Deceptive Pain Expressions." Current Biology. Received: December 7, 2011; Received in revised form: December 6, 2013; Accepted: February 5, 2014; Published Online: March 20, 2014. DOI: dx.doi.org/10.1016/j.cub.2014.02.009

Related Stories

Determination might be a very human expression

March 6, 2014
Humans might be using facial expressions of determination as a call for help from others, according to new research.

Eyes are windows to the soul—and evolution

March 20, 2014
Why do we become saucer-eyed from fear and squint from disgust?

Ability to recognise expression tied to listening and emotion

January 6, 2014
West Australian researchers have developed two new tests that examine a typical person's ability to recognise basic facial expressions.

Written all over your face: Humans express four basic emotions rather than six

February 3, 2014
Human beings are emotional creatures whose state of mind can usually be observed through their facial expressions.

Recommended for you

Study: No evidence to support link between violent video games and behaviour

January 16, 2018
Researchers at the University of York have found no evidence to support the theory that video games make players more violent.

Study listens in on speech development in early childhood

January 15, 2018
If you've ever listened in on two toddlers at play, you might have wondered how much of their babbling might get lost in translation. A new study from the University of Toronto provides surprising insights into how much children ...

Study suggests people dislike you more for humblebragging than for regular boasting

January 12, 2018
A team of researchers from Harvard University and UNC-Chapel Hill has conducted a study regarding humblebragging—in which a person boasts about an achievement but tries to make it sound less boastful by minimizing it—and ...

Can writing your 'to-do's' help you to doze? Study suggests jotting down tasks can speed the trip to dreamland

January 11, 2018
Writing a "to-do" list at bedtime may aid in falling asleep, according to a Baylor University study. Research compared sleep patterns of participants who took five minutes to write down upcoming duties versus participants ...

Study identifies brain circuit controlling social behavior

January 11, 2018
A new study by researchers at Roche in Basel, Switzerland has identified a key brain region of the neural circuit that controls social behavior. Increasing the activity of this region, called the habenula, led to social problems ...

Tamper-resistant oxycodone tablets have no impact on overall opioid use

January 11, 2018
The introduction of tamper-resistant opioid tablets does not have an effect on rates of opioid use or harms at a population level, according to a new study led by the National Drug and Alcohol Research Centre (NDARC) at UNSW ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.