A California-based company — Emotient — has deviced a new software that can identify the emotion of a person using a computer. With a digital camera image, the software can recognise whether the person is feeling joy, sadness, surprise, anger, fear, disgust, contempt or any other emotion.
Known as FACET, this technology, the website says, can “perform real-time, frame-by-frame analysis of the emotional responses of users, detecting and tracking expressions of primary emotions and advance emotions as frustration and confusion; overall sentiments, including positive, negative and neutral; blended composites of two or more emotions.” The programme is encoded with 19 Facial Action Units as elaborated by Paul Ekman’s Facial Action Coding System (a system that is used to group facial movements through movements of facial muscles).
The software accurately registers emotions through a single photograph or video frame (taken through a webcam or digital camera) and can capture microexpressions or those minute expressions which pass through someone’s face. It is interesting to note that even when you have a face that is expressionless or neutral, the face emotes some microexpressions which are also recorded on the software.
FACET can be used in therapy for children with autism. Marian Bartlett, Co-founder and Lead Scientist at Emotient and a Research Professor at the University of California, San Diego’s Machine Perception Lab, has been studying the use of facial-recognition software to help people with autism for several years, says an article on www.livescience.com.
Barlett used an earlier version of the software and created a game. Children were asked to mimic the facial expressions of a cartoon character, and using the software, the game assessed the expression that was recreated and gave a score. “This game helps children with autism recognise other people’s emotions through their facial expressions, as well as teaches them how to make facial expressions that express their own feelings,” he says.