In the past, getting a computer to recognize an object as simple as a chair from another object was a tough problem. But then programmers realized that rather than trying to define "chair-ness," it was better to have computers compare thousands of pictures of chairs and recognize things that looked similar. The same principle applies to recognizing people.
"When it comes to more standard recognition, like looking at a mug shot, are probably better than humans." He noted that computers are already quite good in that they can pick out a face 85 percent of the time when searching among a million photos. That is much better than humans can do.
But take a computer out of its "comfort zone," and the situation changes. "When it comes to more difficult situations -- not a full frontal face shot, or a smaller picture, it's harder," Kanade said.
To address this problem, computer scientists are teaching machines to sort through other digital information in a photograph. For example, a computer might be better at re-identifying a person who is wearing a certain piece of clothing. "There are a lot of techniques emerging," Kanade said. "Not perfect, but basically some statistical techniques... lines, small patch of color, or texture," he said.