VisualRank

From Wikipedia, the free encyclopedia

This article may require cleanup to meet Wikipedia's quality standards.
Please improve this article if you can. (June 2008)

This article may not meet the notability guideline for web content. If you are familiar with the subject matter, please expand or rewrite the article to establish its notability. The best way to address this concern is to reference published, third-party sources about the subject. If notability cannot be established, the article is more likely to be considered for redirection, merge or ultimately deletion, per Wikipedia:Guide to deletion.
This article has been tagged since June 2008.

VisualRank is a system for finding and ranking images by analysing and comparing their content, rather than searching image names, Web links or other text.

On 1 May 2008 at the International World Wide Web Conference in Beijing, Google scientists Yushi Jing and Shumeet Baluja made their VisualRank work public in a paper 'PageRank for Product Image Search':

In this paper, we presented a system that used visual cues, instead of solely text information, to determine the rank of images. The idea was simple: find common visual themes in a set of images, and then find a small set of images that best represented those themes. The resulting algorithm wound up being PageRank, but on an entirely inferred graph of image similarities.