Automating the detection of stolen art

From Discovery News:

A cell phone picture could be worth a million dollars — particularly if it's a snapshot of a piece of stolen art.

A new software tool plays detective by automatically comparing cell phone photos with images in a database of stolen art. The technology could help restore stolen goods to their rightful owners and solve the hundreds of art theft cases opened each year in the United States alone.

It could also give art detectives as well as dealers, collectors and auction houses another tool to verify the authenticity of artworks for sale.

Sounds like a pretty simple and practicable idea, patching together well-established technologies. Take a database of images of stolen artworks, and search it using other images and a pattern-matching application. You'll end up with some false positives, of course, but as long as the matching algorithm is reasonably sophisticated, you should still have a useful tool for flagging possible problem paintings for further investigation. I'm not sure about the claimed potential for authentication, however. Matching two images of the same item is trivial in comparison.

For now, the system works on paintings, carpets and coins, but the researchers already have plans to go beyond those.

"Extensions are on the way to make the system suitable for thee-dimensional objects. These extensions will cover sculptures as well as three-dimensional objects in general," said Bertram Nickolay, head of the department Security Technology at the Fraunhofer Institute in Berlin, Germany.

Posted by David on July 15, 2007 1:18 PM