Social networking site Facebook, has reportedly developed an algorithm which can identify people even if their faces are not visible in a photograph. The algorithm has the capability to recognise people in photographs even when their faces are not fully visible.
According to reports, instead of using facial features, the software can identify people using things like, hair style, pose, clothing and body type. This Facebook algorithm can identify people with 83 percent success rate, as shown by tests.
“We humans can already recognise people with these cues quite well. People have characteristic aspects, even if you look at them from the back,” Yann LeCun, head of artificial intelligence at Facebook, was quoted as saying.
For the test, the research team had pulled almost 40,000 public photos from Flickr – some of people with their full face clearly visible, and others where they were turned away – and ran them through a sophisticated neural network.