Facebook has produced an experimental computer vision algorithm that can recognise you from a picture even if your face isn’t showing.
According to New Scientist, the algorithm works by looking for other unique characteristics like your hairdo, clothing, body shape and pose.
This amazing piece of coding has been produced by Facebook’s AI lab, which is run by Yann LeCun.
“There are a lot of cues we use. People have characteristic aspects, even if you look at them from the back,” says LeCun. “For example, you can recognise Mark Zuckerberg very easily, because he always wears a grey T-shirt.”
To test the experimental algorithm, the Facebook team pulled 40,000 public photos from Flickr, some of which showed people with their backs turned. They were able to identify people in those photos with 83 per cent accuracy.
Read More: Best Android Apps
It’s easy to see how this new algorithm could be used to enhance Facebook Moments, the recently launched photo sharing app that bundles your photos according to the people in them, which it determines through facial recognition software.
The power and inherent intrusiveness of this tool (the facial recognition element is baked in) has prompted the EU to ban Facebook Moments on privacy grounds.
Needless to say, the ability to identify people from images even when they’re not posing for a photo raises a whole bunch of new questions over privacy.