Psychology researchers from Glasgow University have just announced that they've developed a facial recognition algorithm that's 100% accurate in their testing. The technique essentially averages 20 photos into one composite but is able to disregard confounding variables like age, lighting, expression and camera equipment used. (I mean, you can see what they did to poor John Travolta.)
From their abstract:
Accurate face recognition is critical for many security applications. Current automatic face-recognition systems are defeated by natural changes in lighting and pose, which often affect face images more profoundly than changes in identity. The only system that can reliably cope with such variability is a human observer who is familiar with the faces concerned. We modeled 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% to 100%, bringing the robust performance of a familiar human to an automated system.
So even if their unworldly claims of 100% accuracy are possible, it seems that you need quite the baseline of photos to reach it. Here's hoping they can—wait, is this a good or a bad thing? I keep forgetting. [article via theregister]