Communications of the ACM
Computer Identifies Authentic Van Gogh
Detail of Van Gogh self-portrait Autumn 1887.
Credit: wikimedia.org
Tilburg University Ph.D. student Igor Berezhnoy has used artificial intelligence to develop new digital technology for analyzing the authenticity of paintings. Berezhnoy has proposed the Method for the Extraction of Complementary Colors as a way to analyze colors in paintings and determine their authenticity. The approach was tested on digital reproductions of paintings by Vincent van Gogh, who started using complementary colors for contours of objects or parts of scenes during his French period.
Moreover, Berezhnoy says his digital analysis method, the Prevailing Orientation Extraction Technique, is capable of detecting the orientation of brush strokes. The computer algorithms also can identify the "fingerprint" of a master and reveal his or her identify.
Working with the Van Gogh Museum and the Kroller-Muller Museum, Berezhnoy tested the computer algorithms on digital reproductions of Van Gogh's paintings. He says the tool will help art historians conduct visual assessments of paintings, but not replace them.
From Tilburg University (Netherlands)
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA 
No entries found