Researchers detect fake art from originals

Jul 09, 2008

As museums continue to digitize their art collections, it becomes increasingly easier for paintings to be forged. Two Penn State researchers are part of an international team working on a digital system to help detect original works from counterfeit ones.

James Z. Wang, associate professor of information sciences and technology, Jia Li, associate professor of statistics, and their colleagues published their work in the July issue of IEEE Signal Processing.

The team's findings are based on 101 high-resolution grayscale scans of van Gogh paintings provided by the Van Gogh and Kröller-Müller Museums in the Netherlands. Wang and Li broke each scan down into sections measuring 512 by 512 pixels, or about 2.5 by 2.5 inches in canvas size, and analyzed them based on patterns and geometric characteristics of the brush strokes.

From the 101 scans received from the museums, art historians identified 23 as unquestionably authentic van Gogh works. These were used by the computer system as a training database for van Gogh's brushstroke styles.

Statistical models were created to capture the unique style, or "handwriting," that became the artist's signature in 23 of the scans. The other 78 -- either works of van Gogh, works of van Gogh's peers or paintings that had at one time been attributed to him but later found to be unauthentic -- were compared against the generated models to test the algorithms.

Wang and Li, along with computer science and engineering doctoral student Weina Ge, compiled those findings into an online system that allows any painting to be compared against existing data to help determine its authenticity.

The painting analysis project results were first presented at a workshop at the Van Gogh Museum in May 2007. Other authors of the paper, "Image Processing for Artist Identification: Computerized Analysis for Vincent van Gogh's Painting Brushstrokes" include: C. Richard Johnson Jr., Cornell University; Ella Hendriks, Van Gogh Museum; Igor J. Berezhnoy, Phillips Research Europe; Eugene Brevdo, Shannon M. Hughes and Ingrid Daubechies, Princeton University; and Eric Postma, Maastricht University.

Although the research in this field is just starting, Wang said he is confident about its future.

"I believe it is very important to study arts and cultural heritages. Through tackling these tough problems, we can advance the core technologies at the same time," he said. "I anticipate computer scientists, art historians and mathematicians to collaborate more in the future."

The project was recently featured on the PBS TV show NOVA:ScienceNow, where they identified a forged van Gogh among a group of six paintings. The National Science Foundation supported this work.

For more information on the digital painting analysis project, visit: www.digitalpaintinganalysis.org

Source: Penn State

Explore further: Computer-assisted authoring tools help to create complex interactive narratives

add to favorites email to friend print save as pdf

Related Stories

Red color slowly disappearing from Van Gogh's paintings

Dec 16, 2014

Recent scientific research has revealed that the blue irises in Van Gogh's Field with Irises near Arles were once purple. That is because the red is slowly disappearing from Van Gogh's paintings. The discolouration ...

Van Gogh painting under the microscope

Nov 13, 2014

A minute paint sample from Vincent van Gogh's "Sunflowers" painting in Amsterdam is under the microscope at The University of Queensland in Brisbane.

Recommended for you

New paper focuses on degree centrality in networks

Feb 26, 2015

Social networks such as Facebook, LinkedIn and Twitter play an increasingly central role in our lives. Centrality is also an important concept in the theory of social networks. Centrality of an individual, called a "node" ...

Linguists tackle computational analysis of grammar

Feb 26, 2015

Children don't have to be told that "cat" and "cats" are variants of the same word—they pick it up just by listening. To a computer, though, they're as different as, well, cats and dogs. Yet it's computers ...

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.