Goolge has unveiled a cutting-edge image ranking technology "VisualRank" for ranking similar images at the International World Wide Web Conference, according to media reports Tuesday.
VisualRank is positioned as PageRank for images. Google's PageRank helps determine a site's value, based on content and scaled from 0-10. The higher the PageRank, the higher the site appears in organic search listings for related keywords.
Image search today largely relies on analyzing the text near the image, the image's file name and the words in ALT text associated with them.
Despite decades of effort, image analysis remains a largely unsolved problem in computer science, researchers said. For example, while progress has been made in automatic face detection in images, finding other objects such as mountains or tea pots, which are instantly recognizable to humans, has lagged.
The method in Google's paper changes that. A group of images retrieved for a query using traditional search methods is then further analyzed. Image recognition software finds which images in the group seem most similar to each other. It then estimates "visual hyperlinks" between them to produce a final ranking.
"We wanted to incorporate all of the stuff that is happening in computer vision and put it in a Web framework," said Shumeet Baluja, a senior staff researcher at Google.
To develop VisualRank, Google researchers focused on the 2,000 most popular product queries on Google, including iPod, Xbox and Zune. They later determined the top 10 images from its ranking system, gleaned in part from Google Image Search results.
Source: Xinhua/agenciesAuthor：china business Time：2008-05-24 From：china daily
