London: An experimental algorithm developed by Facebook’s artificial intelligence lab can recognise people in photographs even when their faces are hidden. The algorithm will recognise a person through their unique characteristics such as hairdo, clothing, body shape and pose. Yann LeCun, head of artificial intelligence at Facebook, wanted to see if modern face-recognition algorithms could be adapted to recognise people in situations where someone’s face is not clear, something humans can already do quite well.
The research team 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.
The final algorithm was able to recognise individual people’s identities with 83 per cent accuracy, ‘New Scientist’ reported. LeCun said such a tool would be useful for people who are privacy-conscious as it could alert them whenever a photo of themselves, however obscured, pops up on the internet. However, the ability to identify someone even when they are not looking at the camera raises some serious privacy implications.
“If, even when you hide your face, you can be successfully linked to your identify, that will certainly concern people,” said Ralph Gross at Carnegie Mellon University in Pittsburgh, Pennsylvania.