A team of scientists at the University of Bradford in the UK has developed computer software that can tell apart a fake smile from a real one. The research confirms that a spontaneous, genuine smile truly lies in a person's eyes.
Such software to spot false expressions can help improve interactions between machines and humans in the future and assist mental health practitioners in understanding their patients better.
"A smile is perhaps the most common facial expression and is a powerful way of signaling positive emotions. Techniques for analyzing human facial expressions have advanced dramatically in recent years, but distinguishing between genuine and posed smiles remains a challenge because humans are not good at picking up the relevant cues," Hassan Ugail, a professor at the University of Bradford, says in a statement.
How it works
The software works by first mapping a person's face in video recordings and identifying different features such as the person's mouth, cheeks, and eyes.
It then measures how these facial features move through the smile's progress and calculates the differences in movement between the video clips showing real and fake smiles.
According to the scientists, the most significant movements detected by the software were around th+F244e eyes, supporting popular theories that a spontaneous, genuine smile can be seen in a person's eyes.
The team found significant differences in the way people's mouths and cheeks move when comparing the real and fake expressions. However, the movements around the subjects' eyes showed the most striking variation, with genuine smiles generating at least 10 percent more movement in these muscles.
"We use two main sets of muscles when we smile the zygomaticus major, which is responsible for the curling upwards of the mouth, and the orbicularis oculi, which causes crinkling around our eyes," says Ugail, who led the research published in the journal Advanced Engineering Informatics.
"In fake smiles, it is often only the mouth muscles which move, but, as humans, we often don't spot the lack of movement around the eyes. The computer software can spot this much more reliably," he adds.
Ugail says an objective way of analyzing whether an expression is genuine could help develop improved interactions between computers and humans, for example, in biometric identification. "It could also be important to social and clinical scientists aiming to gain more insight into human behavior and emotion."