Facebook is continuing to prove that it is more than just a social media network by developing face recognition technology that can match faces with great accuracy.
Facebook’s DeepFace software uses artificial intelligence to help create facial recognition technology that is 25 percent more effective than existing methods.
“You normally don’t see that sort of improvement,” stated Yanif Taigman, a member of the research team.
Facebook has over 140 billion photos in their library and were able to match all most all of them with a high degree of accuracy, even if they were not tagged.
DeepFace uses 3D face modelling and a nine layer deep neural network that results in a 97 percent accurate rate which is on par with humans.
This “deep learning” technology, supported by Artificial Intelligence, holds a lot of promise for Facebook who believes it is very much the way of the future. Deep learning refers to simulated networks of brain cells to process data and when translated into software, it can help recognize objects and photos.
The DeepFace algorithms are currently purely being used for research purposes only and Facebook has assured users that they are not breaching user privacy.