Tumblr
The social media giant is further developing its facial verification technology to make it nearly as accurate as the human eye, according to a new blog post from the company and a report from MIT Technology Review.
When asked if the faces of two unfamiliar people are the same, the average human will answer correctly 97.53 percent of the time, MIT says. Facebook's technology will be able to tell faces apart 97.25 percent of the time, which the company says is 25 percent more accurate than it was before.
Facebook's new software, known as DeepFace, performs facial verification-which distinguishes whether or not two images show the same face. This is not to be confused with facial recognition, which helps put a name to the face, although Facebook's Yaniv Taiman, who works on the company's AI team, tells MIT that DeepFace may improve facial recognition as well.
DeepFace accomplishes this in two steps. First, it corrects the subject's face so that the person is facing forward in the image. It uses a 3D model of an "average" forward-looking face to nail down this angle. Then, the software uses a method known as deep learning, which means it simulates a neural network that can create a numerical description of reoriented face. If the software finds similar enough facial descriptions for two different images, it concludes that they must be the same face.
Facial verification isn't new to Facebook. In fact, the social network began suggesting friends in tagged photos back in 2010. The DeepFace software, however, will likely prevent the website from mistakenly tagging you in photos as a friend that may have similar facial features.
DeepFace is just a research project for now, according to MIT, but researchers will be presenting the technology at the IEEE Conference on Computer Vision and Pattern Recognition in June.