Researchers from the University of Girona and the Max Planck Institute have demonstrated that certain mathematical algorithms can offer clues about a painting's artistic style, although this is still a far cry from human-like artistic interpretation.
The research team has shown that some artificial vision algorithms can enable a computer to "understand" an image and distinguish artistic styles based on low-level pictorial data, which covers such aspects as brush thickness, the type of material, and the composition of the color palette. Medium-level information encompasses differentiation between certain objects and scenes appearing in an image, as well as the type of painting. High-level information accounts for the historical context as well as knowledge of the artists and artistic trends. "It will never be possible to precisely determine mathematically an artistic period nor to measure the human response to a work of art, but we can look for trends," says study co-author Miquel Feixas.
The researchers' analysis of various artificial vision algorithms used for art classification discovered that certain aesthetic measurements — calculating the order of the image by examining pixels and color distribution — along with the composition and diversity of the color palette, can be helpful. The researchers plan to apply their work to the development of image viewing and analysis tools, the classification of and search for museum collections, the creation of public informative and entertainment gear, and a better understanding of the interplay between people, computers, and works of art.
From Plataforma SINC (Spain)
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA