Criminals worldwide, beware! Psychology researchers at Glasgow University claim to have perfected an automated face recognition algorithm to 100%, which translates to sheer perfection.
We modelled human familiarity by using image averaging to derive stable face representations from naturally varying photographs. This simple procedure increased the accuracy of an industry standard face-recognition algorithm from 54 per cent to 100 per cent, bringing the robust performance of a familiar human to an automated system.
100% reliability? I suppose police and the relevant authorities like the sound of that. For those thinking of doing the crime and not the time, make sure you aren’t too narcissistic and plaster photos of your mug all over your social networking sites.