Facebook now has the ability to recognize a person in photographs even when their face can't be seen.
The company is testing out a new algorithm in its artificial intelligence lab that uses cues such as hairstyles, clothing or even body language to identify a person. It is so good, according to New Scientist, that it can pick a person out of a lineup.
"There are a lot of cues we use. People have characteristic aspects, even if you look at them from the back," Yann LeCun, head of artificial intelligence at Facebook, told New Scientist. "For example, you can recognize Mark Zuckerberg very easily, because he always wears a gray T-shirt."
The latest advances in facial recognition software build on earlier breakthroughs from Facebook as it gets better and better at the business of photo tagging.
Last year, Facebook researchers published a paper about a newly designed facial recognition system with 97.25 percent accuracy -- a mere .28 percent less than a human being. The project, called DeepFace, performed better than most facial recognition systems when measured against a data set commonly used to judge the effectiveness of these systems.
First reported by MIT Technology Review, the development of DeepFace represents a significant advancement over previous facial recognition systems. This is due to the new approach to artificial intelligence known as "deep learning," in which networks of simulated neurons learn to recognize patterns in large amounts of data.
In Facebook's latest work, New Scientist reports that the research team pulled almost 40,000 public photos from Flickr -- some people with their faces visible, others who are obscured -- and ran them through a sophisticated neural network.
The final algorithm recognized individual people's identities 83 percent of the time. It was presented earlier this month at the Computer Vision and Pattern Recognition conference in Boston, Massachusetts.
In the near term, this software could be used with photo apps like Facebook's Moments that was released last week. The app sorts through your photos, categorizing them and then tags people it recognizes as a friend of the Facebook user.
The software could also have privacy benefits, LeCun said: It could be used to alert users when their photo turns up on the Internet without their permission.