So you’ve heard of facial recognition used in user interfaces, on Facebook, and even as a law enforcement tool. But how about using it to identify 15th century works of art?

Three University of California, Riverside academics recently won a $25,000 startup grant in the "digital humanities" from the National Endowment for the Humanities. They'll use the money for a research project that would use facial recognition technology in areas that it historically hasn’t been used in.

"What we want to do is to see to what extent facial recognition is applicable to art." Conrad Rudolph, a professor of art history at UC Riverside, told Ars on Monday. "We just want to see what the limits are according to the current technology."

He said that while art historians are trained in being able to recognize technique, style, and material used, such technology would "add a new body of information that has an objectivity to it." The first round of testing will begin on the known death mask of Battista Sforza, a 15th-century Italian duchess, comparing it to a sculpture that is attributed to her, but is not known with complete confidence.

The research will use the "elastic bunch graph approach," (PDF) first described by a German scientist in 1999. The technique can solve the problem of image variation with respect to facial expression, head position, pose, and size.

Read the comments on this post

Our brains are made to find faces. In fact, they’re so good at picking out human-like mugs we sometimes see them in a jumble of rocks, a bilious cloud of volcanic ash, or some craters on Moon.

But another amazing thing about our brain is that we’re never actually fooled into thinking it’s a real person looking back at us. We might do a second take, but most normal brains can tell the difference between a man and the Moon.

Read the comments on this post