Averaging thousands of images into one


UC Berkeley researchers demonstrated software that averages thousands of similar photo to create a single representative image, like this wedding shot. Users can also refine and weight specific features within the source pool of photos to refine the average image.

"We have this enormous collection of images on the Web, but much of it remains unseen by humans because it is so vast," says computer science professor Alexei Efros. "People have called it the dark matter of the Internet. We wanted to figure out a way to quickly visualize this data by systematically 'averaging' the images."

"Software Creates One Picture That Says It All" (Smithsonian)

Video accompanying the UC Berkeley press release: