Facebook can recognize you even if your face isn’t visible

Thanks to advances in computer vision, we now have machines that can pick you out of a lineup. But what if your face is hidden from view? An experimental algorithm out of Facebook’s artificial intelligence lab can recognize people in photographs even when it can’t make out their faces. Instead, it looks for other characteristics, such as hairdo, clothing, body shape and pose.

Modern face-recognition algorithms have already found their way into social networks, shops and even churches. Yann LeCun, head of artificial intelligence at Facebook, wanted to see whether they could be adapted for situations where someone’s face isn’t clear, something humans can do quite well. “There are a lot of cues we use. People have characteristic aspects, even if you look at them from the back,” LeCun says. “For example, you can recognize Mark Zuckerberg very easily, because he always wears a gray T-shirt.” The research team pulled almost 40,000 public photos from Flickr -- in some, the person’s full face was clearly visible; in others, the face was turned away from the camera -- and ran them through a sophisticated neural network. The final algorithm was able to recognize individuals with 83 percent accuracy.