Computers can now recognize 21 different emotions
Ever wondered if you look happily disgusted? Or sadly angry? There may one day be an app for that.
US researchers have uncovered a way for computers to recognize 21 distinct and often complex facial expressions, in what is being hailed as a breakthrough in the field of cognitive analysis.
A team from Ohio State University devised a way for computers to pinpoint more than triple the number of documented facial expressions than currently can be detected.
“We’ve gone beyond facial expressions for simple emotions like ‘happy’ or ‘sad.’ We found a strong consistency in how people move their facial muscles to express 21 categories of emotions,” said Aleix Martinez, a cognitive scientist and associate professor of electrical and computer engineering at Ohio State.
“That is simply stunning. That tells us that these 21 emotions are expressed in the same way by nearly everyone, at least in our culture.”
The research, detailed in the current issue of the Proceedings of the National Academy of Sciences, could eventually aid the diagnosis and treatment of mental conditions such as autism and post-traumatic stress disorder.
Until now, cognitive scientists have limited their studies to tracking six basic emotions — happy, sad, fearful, angry, surprised and disgusted.
However, Ohio researchers have been able to vastly increase the range of detectable emotions after photographing the responses of 230 volunteers to verbal cues such as “you just got some great unexpected news” (“happily surprised”), or “you smell a bad odor” (“disgusted”).
Painstaking analysis of the resulting 5,000 images allowed researchers to pinpoint variations on prominent landmarks for facial muscles, such as the corners of the mouth or the outer edge of the eyebrow.
The researchers pored over data from the Facial Action Coding System or FACS, a standard tool in body language analysis, checking for similarities and differences in expressions.
As a result they were able to uncover 21 emotions — the six basic emotions — plus “compound emotions” which were a combination.
For example, “happily surprised,” was a reaction to someone receiving unexpected good news.
Researchers were able to identify the emotion after analyzing the expressions for happy — a drawing up of the cheeks into a smile — and surprise, which saw participants widen their eyes and allow their mouths to drop open.
In 93 percent of cases, participants reflected “happily surprised” with a mixture of the two reactions for “happy” and “surprised.”