acm-header
Sign In

Communications of the ACM

ACM TechNews

Can an Algorithm Tell US Who Influenced an Artist?


View as: Print Mobile App Share:
An algorithm under development at Rutgers University found similar elements in Vincent van Goghs Old Vineyard with Peasant Woman 1890 and Joan Miros The Farm 1922 (shown here).

Computer scientists at Rutgers University are developing an algorithm that picks up similarities between images of paintings.

Credit: Rutgers University Department of Computer Science

Rutgers University researchers are training a computer to analyze thousands of paintings to understand which artists influenced others.

The software scans digital images of paintings looking for common features, such as composition, color, line, and objects shown in the piece. The software identifies paintings that share visual elements, suggesting the earlier painting's artist influenced the later one's.

The software found some connections art historians had not, according to Rutgers professor Ahmed Elgammal. "The advantage is it can easily mine thousands and millions of art works in a very [efficient] way," Elgammal says.

Although detecting similarities between paintings can help art historians discover possible influences, the software cannot definitively establish a connection between two artists. "Our final goal is not to get a final answer," Elgammal says. Instead, he says it will "be a tool to art historians, so it can help them do their job."

The project is part of a broader effort at Rutgers to apply computer science techniques to the humanities. The art program is one of the first projects of Rutgers' Digital Humanities Lab, which it established this year in its Computational Biomedicine Imaging and Modeling Center.

From The Washington Post
View Full Article - May Require Free Registration

 

Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


 

No entries found