Communications of the ACM
Computers Identify What Makes Abstract Art Move US
Credit: CianelliStudios.com
University of Trento researchers have developed a machine-vision system that can measure how color and shapes are distributed in abstract art. The system also used data on how 100 volunteers responded to the paintings to determine the emotional impact of the artistic elements.
To test the system, the researchers gave the program other works of art and asked it to predict the typical viewer's emotional response, ranging from extremely negative to extremely positive. About 80 percent of the time, the system was able to produce a score that matched the average response from a new group of 100 volunteers. The research could lead to using emotional data in the creation of more advanced machine art, says Penn State University professor James Wang.
Similar machine-vision systems also could help improve the Painting Fool, an artificial intelligence-based program developed by Imperial College London researcher Simon Colton. He says that with the ability to identify those aspects of an image that elicit emotion, the Painting Fool could choose a basic theme for a piece, scan the Web to find strongly emotional images, and use the results to create original pieces.
From New Scientist
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found