FB pixel

Researchers develop gender recognition based on smile dynamics

Categories Biometric R&D  |  Biometrics News

Men and women smile differently, in measurable ways that can be used by artificial intelligence to recognize the gender of an individual based on dynamic movement, rather than fixed points, ScienceDaily reports.

A team of researchers from the University of Bradford, led by Professor Hassan Ugail, mapped 49 facial characteristics to assess how underlying muscle movements of a smiling face, and found noticeable differences, such as that women’s smiles are more expansive. The team created an algorithm based on the differences and tested it against video footage of 109 subjects, with 86 percent accuracy, which the researchers believe could easily be improved.

“We used a fairly simple machine classification for this research as we were just testing the concept, but more sophisticated AI would improve the recognition rates,” Ugail says.

Some leading facial recognition systems have previously been shown to identify women significantly less accurately than men.

The team hopes to investigate questions raised by the research in future projects, such as how the AI would respond to transgender people or those who have had plastic surgery.

“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,” according to Ugail.

Recent research shows that gender can be identified based on keystroke dynamics, while a blog post from R7 Speech Sciences co-founder Delip Rao explored the inherent challenges in making speech recognition as accurate for women as for men.

Related Posts

Article Topics

 |   |   | 

Latest Biometrics News


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

ID16.9 Podcast

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics