Researchers at Tel-Aviv and Zhejiang universities have developed software that identifies the key features of an image based on the color and shape. The elements’ positioning is used to judge a photo, then changed to improve it, says Tel-Aviv’s Lior Wolf. The software uses color and shape to isolate objects in an image. The program then decides which are the most important or salient to the image. “For example, if there are many lines or contrasting colors in a region, then it would have a high saliency score,” Wolf says. These salient features are judged against composition rules commonly included in camera manuals, such as the rule of thirds. The system also tweaks the position of prominent diagonal lines and positions important objects around the central point of the image. The researchers tested the system by manually altering photos to destroy their aesthetics. The software changed the images to make them similar to the originals. The program fits with a recent trend for easy-to-use creative software, says Nanyang Technological University’s Martin Constable.
For More Information Visit: http://www.cpccci.com
Tags: software
This entry was posted on Tuesday, February 16th, 2010 at 8:23 pm and is filed under Computer Science and Engineering News. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.