Forget "facial" recognition. Facebook is getting so good at identifying you in photos that it doesn't even need to see your mug.

According to New Scientist, the social network has developed an "experimental" algorithm that can identify you in photos without seeing your face. Instead, it uses other characteristics—like your hair, clothing, body shape, and how you carry yourself—to figure out it's you.

Facebook's head of artificial intelligence, Yann LeCun, told the news outlet that the new algorithm mimics how a human would recognize another person.

"There are a lot of cues we use," LeCun said. "People have characteristic aspects, even if you look at them from the back. For example, you can recognize Mark Zuckerberg very easily, because he always wears a gray T-shirt."

To test the new algorithm, the Facebook team pulled nearly 40,000 public photos from Flickr offering a variety of face shots and snaps where people were looking away. The team then ran these photos through its "sophisticated neural network" and the algorithm was able to identify people with 83 percent accuracy, according to the report.

New Scientist notes that Facebook may in the future integrate this new technology into its photo-sharing app Moments, which has drawn criticism from privacy advocates over its use of facial-recognition technology. The app, launched last week in the U.S., groups images on your phone based on when they were taken and, using facial-recognition software, which friends are in them.

That facial-recognition bit has European regulators up in arms, and until Facebook develops a way for users to opt-in to facial recognition, Moments won't be launching in the EU.

But while this new technology goes a step further than facial recognition, Facebook's LeCun said it could actually be good for privacy. It might, for example, alert someone if their photo shows up online, even if they are in the background or facing away from the camera, she told New Scientist.