IT and society: Computer “spots art fakes”

The approach, known as "sparse coding" analysis, builds a virtual library of an artist's works and breaks them down into the simplest possible visual elements.

The researchers claim that verifiable works by the artist can be rebuilt using varying proportions of those simple elements, while imitators' works cannot.

The work is reported in Proceedings of the National Academy of Sciences of the United States of America (PNAS).

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 team tried the approach on the works of Pieter Bruegel the Elder, a 16th century Flemish painter whose original works are well-known and who had a number of imitators.

Upon using the sparse coding approach on the artist's known works, the team of researchers showed that the optimised basis functions were unable to reproduce the imitations.