What caricature can teach computers about facial recognition

Wired magazine has an interesting article on the limits of facial recognition and what the art of caricature could teach those trying to make computer recognition possible. Ben Austen talks to caricature artists Stephen Silver, Jason Seiler, Roger Hurtado, and Court Jones.

?I don?t care how many wrinkles there are around the eye or if there?s stubble,? he says. ?Those features aren?t going to help me. You know who a person is from basic shapes.? He spies a red-haired woman across the room, takes aim at her head. ?Do you see how its meat is all on the outside?? he asks. ?With the features crammed into the center?? Next his sights shift to an African-American woman drawing busily at a foldout table. Her head is actually tiny, Silver points out, but the span from her bottom lip to the base of her neck is immense.

This sort of instant insight is precisely what computers have trouble generating. ?The miraculous thing about caricature artists is that they?re able to zero in on the most distinctive aspect of somebody,? says Erik Learned-Miller of the Computer Vision Laboratory at the University of Massachusetts, Amherst. ?We still don?t know how to do that in computer vision. People are working very hard to write programs that find just that combination of two or three things that give a person away.?