Software Scans for Stolen Art

July 13, 2007 — 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.

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.

Nickolay developed the technology with Christian Veenhuis, a research associate also the institute.

Databases of missing art already exist, maintained by groups such as the Art Loss Register, an international nonprofit agency, and Interpol, a worldwide criminal police organization. But these databases contain a huge assembly of descriptions and images of the stolen property that can be time-consuming for an investigator to sort through.

The image analysis software makes sorting through heaps of stolen art automatic, said Nickolay.

It works like this: At the sight of a suspicious piece of art, the investigator snaps a photo using a cell phone. Software in the phone automatically calls a number that connects to a central computer server. The digital picture is transferred and an image analysis program compares the snapshot with photos in the database.

It takes about 30 to 40 seconds for the software to transfer the image, identify the shape, outline, color and texture of objects in the original image and return a top ten list of closest matches to the detective.

"If the painting is clearly registered as stolen, the investigator has to confiscate it. But the exact procedure depends on the law of the appropriate country where the auction takes place," said Nickolay.

Julian Radcliffe, chairman of the Art Loss Register headquartered in London, has looked into image recognition technology as a way to spot stolen art, but expressed skepticism. "None of the image matching is good enough to repace the art historians we use," he said.

According to Radcliffe, searches for stolen art happen weeks before an auction. Art historians, who typically speak three or four different languages and are well-versed in the jargon of fine art, use details from auction catalogs to search their computer database for matches.

Nickolay and Veenhuis are currently investigating other uses for the image analysis system, such as exposing counterfeits.