This new technique can predict your gender based on smiles

Scientists have developed a novel artificial intelligence (AI) technique that can predict the gender based on the smile.

This new technique can predict your gender based on smiles
Representational image

London: Scientists have developed a novel artificial intelligence (AI) technique that can predict the gender based on the smile.

The new method based AI uses the dynamic movement or a video of the smile to automatically distinguish between men and women,

The existing automatic gender recognition techniques use only static images and compared fixed facial features to recognise smiles.

In the study, led by Hassan Ugail, a professor at Britain's University of Bradford, 49 landmarks were mapped on the face, mainly around the eyes, mouth and down the nose.

Then they used these to assess how the face changes as we smile caused by the underlying muscle movements -- including both changes in distances between the different points and the 'flow' of the smile.

The results showed noticeable differences between men and women and that women's smiles were more expansive.

Hassan Ugail said,"Anecdotally, women are thought to be more expressive in how they smile, and our research has borne this out. Women definitely have broader smiles, expanding their mouth and lip area far more than men."

For the study, the team created an algorithm using their analysis and tested it against video footage of more than 100 people as they smiled.

The computer was able to correctly determine gender in 86 per cent of cases and the team believe the accuracy could easily be improved.

Ugail said,"Because this system measures the underlying muscle movement of the face during a smile, we believe these dynamics will remain the same even if external physical features change, following surgery for example."

"This kind of facial recognition could become a next- generation biometric, as it's not dependent on one feature, but on a dynamic that's unique to an individual and would be very difficult to mimic or alter," he noted.

The study was published in The Visual Computer: International Journal of Computer Graphics.

(With IANS inputs)

By continuing to use the site, you agree to the use of cookies. You can find out more by clicking this link

Close