Facebook's DeepFace aims to see you for who you really are

The social network's artificial intelligence group is digging into sophisticated software for matching faces in photos with human-level accuracy.

Matt Harnack/Facebook

Facebook is working on artificial intelligence software called DeepFace that is capable of matching faces in images with nearly the same accuracy as humans.

The social network's DeepFace system uses a 3D modeling technique to detect faces, and crop and warp them so that they face front, a method known as frontalization.

The software, currently in testing, is a facial verification system and differs from facial recognition in that it matches faces in large data sets, as opposed to assigning identity to faces. In essence, DeepFace can scan millions of photos, virtually rotate and correct the images, and find all matching faces.

Facebook's DeepFace alignment system uses 2D and 3D facial modeling and deep learning to arrive at a final frontalized crop (g). Facebook

The sophisticated system was trained using a data set of more than 4 million facial images of 4,000 people. Facebook's method proved accurate 97.25 percent of the time, according to the company's recently published paper, "DeepFace: Closing the Gap to Human-Level Performance in Face Verification."

Though still in the research and development stages, Facebook's proposed system purports to reduce the error of the current state of facial matching technologies by more than 25 percent.

Facebook's AI Group will present its research at the Conference on Computer Vision and Pattern Recognition in June.

[via MIT Technology Review]

Featured Video
This content is rated TV-MA, and is for viewers 18 years or older. Are you of age?
Sorry, you are not old enough to view this content.

Details about Apple's 'spaceship' campus from the drone pilot who flies over it

MyithZ has one of the most popular aerial photography channels on YouTube. With the exception of revealing his identity, he is an open book as he shares with CNET's Brian Tong the drone hardware he uses to capture flyover shots of the construction of Apple's new campus, which looks remarkably like an alien craft.

by Brian Tong