Technology 3 min read

Researchers Develop Software to Spot Fake Facial Expressions

As more and more machine learning systems are developed to spot manipulated images, a team of researchers from the University of Bradford developed a computer software that can detect false facial expressions.

Image courtesy of Shutterstuck

Image courtesy of Shutterstuck

It’s not always easy to tell fake and real smiles apart. So, the researchers at the University of Bradford developed computer software that does just that – spot false facial expressions.

The software analyzes the movement of the smile across a face to determine how genuine the expression is. While capturing the facial expression, the software focuses more on the eyes, thus confirming the belief that a spontaneous, genuine smile comes from the eyes.

In a statement, lead researcher of the study and professor of Visual Computing at the University of Bradford, Hassan Ugail, said:

“A smile is perhaps the most common of facial expressions 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.”

So, how does the software spot fake smiles?

How the Program Identifies False Facial Expressions

First, the software maps a person’s face from within a video recording. It identifies the subject’s mouth, cheeks, as well as the eyes, and measures the movement of these facial features during a smile. Finally, the program calculates the differences in movement between the video clips showing a fake smile and those showing real ones.

After developing the software, the researchers had to conduct a test.

For this part, the researchers used two datasets — the first contained images of people expressing genuine smile, while the other portrayed individuals with posed smiles.

Alongside significant differences in the way the subjects’ mouths and cheeks moved, the researchers noted that the eye movement showed the highest variation. The findings showed that participants with real smiles generated at least 10 percent more muscle movement than those with false expressions.

Professor Ugail explained:

“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. 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.”

The researchers believe that an ability to accurately identify false facial expressions could improve our interaction with machines, especially in biometric identification. Also, it could come in handy for social and clinical scientists for providing an insight into human emotions and behavior.

Read More: Emotional AI Will Soon see Right Through Your Poker Face

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.