Site icon Wonderful Engineering

AI Can Now Tell If The Person Is A Male Or Female By Reading Their Lips

gender study AI

A new AI can predict the gender based on your smile. A team of researchers at the University of Bradford have developed the AI after noticing some marked differences between ‘male’ and ‘female’ smiles. They are expecting to study the ways in which cosmetic procedures can affect these differences and how the research applies to the transgender community. The AI is a step ahead in the already existing technology which can determine the gender of a person based on a picture of their smile.

The report stated, “Although automatic gender recognition is already available, existing methods use static images and compare fixed facial features. The new research is the first to use the dynamic movement of the smile to automatically distinguish between men and women.” To carry out the study, researchers mapped out 49 landmarks of the face. All these landmarks are found mostly around the eyes, down the nose, and near the mouth. The analysis said, “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: how much, how far and how fast the different points on the face moved as the smile was formed.”

After that, the researchers analyzed whether or not there were significant differences between women and men’s smiles. They concluded that there were and they said that the women’s smiles are more expansive than men’s. Hassan Ugail, a researcher professor 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.”

The team has built an algorithm based on the analysis and it was tested using video footage of more than 100 individuals smiling. The report said that the algorithm was able to correctly determine gender in 86% of the cases and the accuracy can be further enhanced. Professor Ugail also said that the technology can be made better. He said, “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.” The study said that the research was done to enhance machine learning capabilities.

The study states, “One is how the machine might respond to the smile of a transgender person, and the other is the impact of plastic surgery on recognition rates.” Professor 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.”

Exit mobile version