January 5, 2010
Pieter Bruegel the Elder was a 16th-century painter from the Netherlands known for his landscape paintings populated by peasants (though you may also be familiar with his version of the Tower of Babel). He also produced dozens of drawings and prints. In the early 1990s, though, several Alpine drawings attributed to Bruegel were identified as fakes when it was discovered they were drawn on paper made after 1569, when the artist died.
Although the identification of the drawings as imitations might have been distressing for the owners of the works, it provided a group of computer scientists with an ideal test case for the development of a statistical method for spotting fake art. Their latest paper appears in this week’s PNAS.
The scientists used a method called “sparse coding” that breaks down an artist’s works into tiny, random pieces that, when recombined, can recreate the original works but not a piece done by another hand. BBC News explains:
The method works by dividing digital versions of all of an artist’s confirmed works into 144 squares – 12 columns of 12 rows each.
Then a set of “basis functions” is constructed – initially a set of random shapes and forms in black and white.
A computer then modifies them until, for any given cut-down piece of the artist’s work, some subset of the basis functions can be combined in some proportion to recreate the piece.
The basis functions are refined further to ensure that the smallest possible number of them is required to generate any given piece – they are the “sparsest” set of functions that reproduces the artist’s work.
This method easily picked out the fake Bruegels from the real ones and did so more easily and accurately than other approaches used to find imitations. “These digital techniques can assist art historians in making judgments and may provide detailed information about subtleties inherent to a particular artist’s style that are not immediately observable,” the scientists write.
Sign up for our free email newsletter and receive the best stories from Smithsonian.com each week.