Researchers Use Machine Learning Algorithm To Pinpoint Brain Activity That Decodes Facial Expressions

A team of researchers at Ohio State University pinpointed the area of the brain that recognizes human facial expression. Their recent study reveals that this region - the posterior superior temporal sulcus (pSTS) - is on the right side of the brain behind the ear. The study utilized functional magnetic resonance imaging (fMRI) to identify the pSTS as the region that is activated when their test subjects viewed images of people making various kinds of facial expressions. Using the subjects' fMRI images and comparing them to facial muscle movements in test photographs, the team created a map of pSTS regions that activate for specific facial muscle groups In addition, the study revealed that particular neural patterns within the pSTS are used for specific facial movements, such as a furrowed brow. "That suggests that our brains decode facial expressions by adding up sets of key muscle movements in the face of the person we are looking at," said Aleix Martinez, a professor of electrical and computer engineering at Ohio State and senior author of the study.