Journal of Personality and Social Philosophy: Detecting sexual orientation from facial images

September 23, 2017

"We show that faces contain much more information about sexual orientation than can be perceived and interpreted by the human brain. We used deep neural networks to extract features from 35,326 facial images. These features were entered into a logistic regression aimed at classifying sexual orientation. Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 74% of cases for women. Human judges achieved much lower accuracy: 61% for men and 54% for women. The accuracy of the algorithm increased to 91% and 83%, respectively, given five facial images per person."

Read More

More Updates

If you’ve come to our site from a search engine like Google or a social platform like Facebook, your information is possibly being collected, tracked, and shared by them. Learn more and/or opt-out of some sharing on CAPrivacy.org.
Your browser has javascript disabled or does not support javascript, some site functionality may not work as a result