US researchers are harnessing digital technology to help differentiate original works of art from forgeries.
Penn State scientists James Z Wang, associate professor of information sciences and technology, and Jia Li, associate professor of statistics, have published their work in the July issue of IEEE Signal Processing.
The team's findings are based on 101 high-resolution greyscale scans of paintings by Vincent van Gogh provided by the Van Gogh and Kröller-Müller museums in the Netherlands.
The scientists broke each scan into sections measuring 512 x 512 pixels, or about 2.5in x 2.5in in canvas size, and analysed the 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 the artist'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 paintings, which were by van Gogh, van Gogh's peers or had at one time been attributed to van Gogh but later found to be unauthentic, were compared against the generated models to test the algorithms.