Translation - Μετάφραση
General => General Discussion => Art => Topic started by: wings on 05 Jan, 2010, 13:36:02
-
Computer method 'spots art fakes'
(https://www.translatum.gr/forum/proxy.php?request=http%3A%2F%2Fnewsimg.bbc.co.uk%2Fmedia%2Fimages%2F47033000%2Fjpg%2F_47033536_n8200093-spl.h.jpg&hash=aebb0c9e86f8e3e72dacbfec96a0ead308d3df6f)
The method spots imitations of works by Pieter Bruegel the Elder
A simple method to distinguish artistic fakes and imitations has been demonstrated by researchers.
The approach, known as "sparse coding", builds a virtual library of an artist's works and breaks them down into the simplest possible visual elements.
Verifiable works by that 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.
The mathematical analysis of artworks is a relatively new discipline, which gained worldwide attention when it emerged in 1999 that Jackson Pollock's "drip paintings" could be cast in the mathematics of fractals - patterns that repeat at ever-smaller scales.
However, the claim that a fractal analysis could be used to identify Pollock-like paintings of unknown provenance remains a subject of some controversy.
Sparse richness
Since that time, a number of approaches to identify the origins of artworks have been attempted, yielding varying degrees of certainty in the results.
Now, Daniel Rockmore of Dartmouth College in the US and his colleagues have shown a straightforward method known as sparse coding that, so far, appears to be significantly more accurate than previous attempts.
...
Full article at: http://news.bbc.co.uk/2/hi/technology/8440142.stm