Last week at the WWW2008 conference in Beijing, Google engineers presented a paper which will be applied on PageRank system of finding relevant pages to improve the accuracy of image search in Google. This new technology is called VisualRank.
The paper, titled "PageRank for Product Image Search," (PDF) was published by Yushi Jing and Shumeet Baluja of Google. In this paper, they discussed about using a 'visual link structure' in PageRank system and it also proposed to move away from the current search system.
In the proposed system, a numerical weight would be assigned to each image and, according to the paper, ranking would occur based upon "expected user behavior given the visual similarities of the images to be ranked.
Continue at PC World
The paper, titled "PageRank for Product Image Search," (PDF) was published by Yushi Jing and Shumeet Baluja of Google. In this paper, they discussed about using a 'visual link structure' in PageRank system and it also proposed to move away from the current search system.
In the proposed system, a numerical weight would be assigned to each image and, according to the paper, ranking would occur based upon "expected user behavior given the visual similarities of the images to be ranked.
Continue at PC World
Posts
No comments:
Post a Comment