Last week, at the International World Wide Web Conference in Beijing, two Google-affiliated researchers presented a paper called “PageRank for Product Image Search,” trumpeting a fledging algorithm that overhauls the primitive text-based methods used by the company’s current image search technologies.
The research paper is available here. PageRank is an algorithm for ranking web pages which was introduced by Google nearly a decade ago. Now, the company says, it has a technology that can do much the same for online image search.
Our experiment results show significant improvement, in terms of user satisfaction and relevancy, in comparison to the most recent Google Image Search results.
Shumeet Baluja and Yushi Jing tell the world from the pages of their research paper.
Google’s current algorithm for image search produces mostly incorrect results because it doesn’t look at the image and instead examines the text surrounding those images. For example you typically take a known image and compare it to other images. You might use a known photo of Paris Hilton, for instance, to find other Paris pics.
By contrast, Google’s PageRank for Product Image Search - also known as “VisualRank” - seeks to actually understand what’s pictured. It looks for “visual themes” across a collection of images, before ranking each image based on how well it matches those themes.But the technology goes beyond classic image recognition, which can be time consuming and/or expensive - and which often breaks down with anything other than faces and a handful of other image types. In an effort to properly identify a wider range of objects, Baluja and Jing have merged existing image processing techniques with the sort of “link analysis” made famous by PageRank.
Through an iterative procedure based on the PageRank computation, a numerical weight is assigned to each image. This measures its relative importance to the other images being considered.
according to the explanation.
0 responses so far
There are no comments yet...Kick things off by filling out the form below.
You must log in to post a comment.