Computers match humans in understanding art

Sep 26, 2012
A computer-generated graph of similarities between 34 different painters, reflecting the similarities between the artistic styles of painters as were automatically deduced by the computer. Credit: Lior Shamir

Understanding and evaluating art has widely been considered as a task meant for humans, until now. Computer scientists Lior Shamir and Jane Tarakhovsky of Lawrence Technological University in Michigan tackled the question "can machines understand art?" The results were very surprising. In fact, an algorithm has been developed that demonstrates computers are able to "understand" art in a fashion very similar to how art historians perform their analysis, mimicking the perception of expert art critiques.

In the experiment, published in the recent issue of ACM Journal on Computing and , the researchers used approximately 1, 000 paintings of 34 well-known artists, and let the analyze the similarity between them based solely on the visual content of the paintings, and without any human guidance. Surprisingly, the computer provided a network of similarities between painters that is largely in agreement with the perception of .

The analysis showed that the computer was clearly able to identify the differences between classical realism and modern artistic styles, and automatically separated the painters into two groups, 18 classical painters and 16 modern painters. Inside these two broad groups the computer identified sub-groups of painters that were part of the same artistic movements. For instance, the computer automatically placed the High Renaissance artists Raphael, , and Michelangelo very close to each other. The Baroque painters Vermeer, Rubens and Rembrandt were also clustered together by the algorithm, showing that the computer automatically identified that these painters share similar artistic styles. The automatic computer analysis is in agreement with the view of historians, who associate these three painters with the Baroque artistic movement. Similarly, the computer algorithm deduced that Gauguin and CĂ©zanne, both considered post-impressionists, have similar artistic styles, and also identified similarities between the styles of Salvador Dali, Max Ernst, and Giorgio de Chirico, all are considered by art historians to be part of the surrealism school of art. Overall, the computer automatically produced an analysis that is in large agreement with the influential links between painters and artistic movements as defined by art historians and critiques.

While the average non-expert can normally make the broad differentiation between modern art and classical realism, they have difficulty telling the difference between closely related schools of art such as Early and High Renaissance or Mannerism and Romanticism. The experiment showed that machines can outperform untrained humans in the analysis of fine art.

The experiment was performed by computing from each painting 4,027 numerical image context descriptors—numbers that reflect the content of the image such as texture, color and shapes in a quantitative fashion. This allows the to reflect very many aspects of the visual content, and use pattern recognition and statistical methods to detect complex patterns of similarities and dissimilarities between the artistic styles and then quantify these similarities.

Explore further: Researchers developing algorithms to detect fake reviews

add to favorites email to friend print save as pdf

Related Stories

Do computers understand art?

Dec 23, 2009

A team of researchers from the University of Girona and the Max Planck Institute in Germany has shown that some mathematical algorithms provide clues about the artistic style of a painting. The composition ...

Computer identifies authentic Van Gogh

Dec 21, 2009

(PhysOrg.com) -- Dutch researcher Igor Berezhnoy has developed computer algorithms to support art historians and other art experts in their visual assessment of paintings. His digital technology is capable ...

A bird's eye view of art

Jun 30, 2009

Pigeons could be art critics yet, according to a new study which shows that like humans, pigeons can be trained to tell the difference between 'good' and 'bad' paintings. According to Professor Shigeru Watanabe from Keio ...

Smithsonian holds vote on video games for exhibit

Feb 21, 2011

(AP) -- The Smithsonian American Art Museum is asking the public to help select video games that will be included in its first exhibit to explore the art and visual effects of gaming.

Professor's algorithms unlock Van Gogh mysteries

Mar 31, 2011

(PhysOrg.com) -- A Cornell electrical engineering professor is helping art historians do a little detective work by using computing algorithms to identify which of Vincent Van Gogh's paintings came from the ...

Recommended for you

Government ups air bag warning to 7.8M vehicles

1 hour ago

The U.S. government is adding more than 3 million vehicles to a rare warning about faulty air bags that have the potential to kill or injure drivers or passengers in a crash.

Fighting cyber-crime one app at a time

1 hour ago

This summer Victoria University of Wellington will be home to four Singaporean students researching cyber threats. The students have been working with Dr Ian Welch, a lecturer in Victoria's School of Engineering and Computer ...

Using sound to picture the world in a new way

1 hour ago

Have you ever thought about using acoustics to collect data? The EAR-IT project has explored this possibility with various pioneering applications that impact on our daily lives. Monitoring traffic density ...

User comments : 1

Adjust slider to filter visible comments by rank

Display comments: newest first

B__
not rated yet Sep 27, 2012
Interesting, now if it worked on contemporary art, then I'd be impressed!