PITTSBURGH--Carnegie Mellon University robotics researcher Vladimir Brajovic has developed a tool that automatically improves the appearance of darkened or underexposed photographs by digitally adding light to dark areas.
The Shadow Illuminator, funded through a $350,000 grant from the National Science Foundation, was developed originally to help robots see better. Using principles based on the physics of how optical images are formed, Shadow Illuminator imitates the vision processes that take place in the human eye. It examines the content of a photograph, estimates the illumination conditions and then brightens shadows. It also enhances details within the shadow.
"Shadow Illuminator is intelligent and works consistently for all pictures," said Brajovic, director of the Computational Sensor Laboratory in Carnegie Mellon's Robotics Institute. "It provides the same results quickly and eliminates the hassle of manually adjusting photographs."
According to Brajovic, traditional image-enhancement tools manipulate the color and intensity of the pixels of an image regardless of its content, relying on human judgment to determine what parts of an image need adjustment. Applying this process to each image can become tedious and time consuming.
"While there are other programs that enable users to manually produce similar results, you have to figure out what works for each individual picture," Brajovic said.
The Shadow Illuminator, which has a patent pending on its technology, is being commercialized by Intrigue Technologies, Inc., a company formed by Brajovic that specializes in software and hardware for electronic imaging under difficult lighting conditions.
Shadow Illuminator can be accessed at www.shadowilluminator.org. Visitors to this free site can upload pictures and apply Shadow Illuminator to achieve brighter, clearer results. For visitors who sign up for a free account, the site also creates a personalized album to hold their uploaded photos.
AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert! system.