Can Technology Topple Art Forgeries?

Jenn McMenemy
Yes, but it needs help!

Appraisers Workshops highlights an interesting article in the NY Times on the use of technology in identifying forged artworks. Being the tech geek that I am, I can't help but share it with you.

Barbara Wall interviews Eric Postma, a professor of artificial intelligence at Tilburg University in the Netherlands. Moreover, Postma is an expert in the digital analysis of Vincent Van Gogh works. Using complex algorithms and applying it to a database of Van Gogh paintings, his software is able to identify a complex pattern of brushstrokes that is unique to the artist. (Sounds like a brushstroke "fingerprint" of sorts.) Here Postma describes how the process has been used to identify fake Van Goghs:

Working in cooperation with the Van Gogh Museum and the Kröller-Müller Museum, both located in the Netherlands, we have been able to demonstrate the accuracy of digital analysis. A painting depicting the sea at Saintes-Maries, a Van Gogh fake sold by the German art dealer Otto Wacker, fooled experts for years, but our software easily identified the work as suspect. It had too many prominent brush strokes.... Our methodology was also tested on a U.S. television show, “Nova Science,” where we were easily able to distinguish one fake Van Gogh painting from five genuine works by the artist.

I find it unfortunate that this method is not being more encouraged in the art world. Postma continues:

We enjoy support from museums in the Netherlands and the United States, but many art historians are still suspicious of our techniques. This is understandable because our algorithms are still being developed. We do not have all the answers, but working together historians and computer scientists would make a formidable team.... We also need to enlarge our database of paintings if we are to offer a full service. I would like to do more work on some of the modern artists, such as Picasso, but many collectors are reluctant to have their expensive works of art held up to scrutiny. Unless we can persuade collectors that it is in the interests of the art world to compile a digitized database of genuine and fake art work, the forgers will always be ahead of the curve.

To me the art world should embrace this technology and help it develop. In addition to brainiacs creating complex algorithms, digital analysis requires a large pool of data/paintings in order to identify that unique characteristic that's going to separate the authentics from the forgeries. Much like people submit works to contribute to catalogues raisonné, they should submit their works for digital analysis. The data is certainly out there and it only stands to benefit the entire art community (well, if you are not the one with the fake, that is.) It's great to see institutions like the Van Gogh Museum and the Kröller-Müller Museum participating in this advancement in technology.