According to Yong Jae Lee, an assistant professor in computer sciences, the system could also be used to help improve the ability of computer vision systems to distinguish key features in an image."
Washington, Aug 15 - A photo is worth a thousand words, but what if the image could also represent thousands of other images? A new tool intends to do so.
A new software developed by computer scientists at University of California Berkeley seeks to tame the vast amount of visual data in the world by generating a single photo that can represent massive clusters of images.
The software called AverageExplorer works by generating an image that literally averages the key features of other photos.
This tool can give users the photographic gist of a kid on Santa's lap, housecats, or brides and grooms at their weddings.
Users can also give extra weight to specific features to create subcategories and quickly sort the image results.
Visual data is among the biggest of Big Data. We have this enormous collection of images on the Web, but much of it remains unseen by humans because it is so vast. People have called it the dark matter of the internet, said Alexei Efros, an associate professor of electrical engineering and computer sciences.
We wanted to figure out a way to quickly visualize this data by systematically 'averaging' the images, he added.
Facebook reports six billion photo uploads per month on its site and YouTube gets 72 hours of video uploaded every minute.
According to Yong Jae Lee, an assistant professor in computer sciences, the system could also be used to help improve the ability of computer vision systems to distinguish key features in an image.
The research was presented at the international conference and exhibition on computer graphics and interactive techniques in Vancouver, Canada.