Communications of the ACM
How Machine Vision Solved One of the Great Mysteries of 20th-Century Surrealist Art
Researchers have developed a method of utilizing machine-vision analysis. to distinguish original paintings from copies.
Credit: Technology Review
A pair of identical paintings attributed to Belgian surrealist artist Rene Magritte has long mystified art experts as to which one is the original.
Researchers Milan Rajkovic and Milos Milovanovic say the process of creating an original work of art is different from the process of copying one, and this difference can be detected using machine-vision analysis. They based their research on an analysis of work by contemporary Dutch artist Charlotte Caspers, who was commissioned a few years ago to create a set of seven artworks using various methods and then to copy them as closely as possible a few days later.
Rajkovic and Milovanovic believe the use of wavelet analysis can discern differences between an original and a copy by transforming a two-dimensional image into a time-frequency representation that can capture information about the painting at various scales; these scales can be regarded as looking at progressively more blurred images of the paintings. Rajkovic and Milovanovic performed their analysis using the red, green, and blue (RGB) channels of a conventional RGB image of each painting, and repeated the analysis for patches of each painting. "For all patches and all the paintings, the mean global complexity of an original painting is larger than the corresponding value of a copy," they say.
From Technology Review
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found