Continuing the trend of computer software that is designed to read human emotions, as previously reported by HNGN, researchers have created a computer algorithm that can spot hidden human emotions using "machine vision," according to Engadget. Although computer software that catches obvious emotions such as happiness or sadness had already been created, this software works by magnifying human facial expressions and catching brief micro-expressions to reveal what people are truly feeling.
The algorithm was created using the micro-expressions of 20 subjects, which the researchers classified in terms of emotional meaning - positive, surprise and negative, according to the Daily Mail. Using this archive, they taught their algorithm to detect human micro-expressions and reveal the hidden emotions written on the user's face.
Psychologists have long studied micro-expressions and the way they can help reveal the true meaning behind false statements and emotions, according to R&D.
"In high-stake situations...an ME (micro-expression) fleeting across the face could give away a criminal pretending to be innocent, as the face is telling a different story than his statements," said researchers from the University of Oulu in Finland.
"Meanwhile, in computer vision, many research groups have accumulated experience in analyzing ordinary (facial expressions)," write the researchers. "Algorithms have been reported to achieve (facial recognition) performance of above 90% on frontal view."
The computer algorithm is currently 10 percent more accurate at identifying human micro-expressions than actual human participants.
