New Computer Program Sorts Real Jackson Pollock Paintings from Fakes

Nothing ruins an art museum visit faster than the one person who has to say, "my kid could have made this." Now you can rebut that: No, your kid can't do that—and there's a computer program to prove it.

Artist Jackson Pollock, famous for his drip paintings, had a unique, but unfortunately easily duplicated style. After all, Pollock used a large array of tools and machines—like an electric mixer— to make purposively random "strokes" of paint; gravity was as much to credit as the artist himself. With so many counterfeits floating around, even experts were getting befuddled over what was real and what was not. Thankfully, technology is coming to the rescue: A computer program, detailed in the next issue of International Journal of Arts and Technology, uses the machine vision approach to analyze and identify authentic Pollocks with a 93 percent success rate. Lawrence Technological University's Lior Shamir created the program after becoming interested in the abstract paintings. The program analyzes scans of the work and looks for descriptors that are nearly exclusive to authentic paintings. 

"The human perception of visual art is a complex cognitive task that involves different processing centers in the brain," Shamir said. "The work of Jackson Pollock showed unique physiological and neurological human responses to Pollock's drip paintings."

This new breakthrough shows that while Pollock's work is seemingly random, the art possesses certain unique gestures and textures. So you might want to think twice about trying to sell your child's art to the MoMA.

If you would like to do some sleuthing yourself, Shamir's software is available to the public, and can be found here.