RSS
Email
VisualRank: Google’s Advanced Prototype for Image Search
(Rate this article)
Loading ...Email It!
Dan Neary and Shailesh Rao spoke at the IAMAI India Digital Summit about search moving away from Keywords to natural language search, image search, behavioural search, serendipity search and tagging.
Well here is something that should be able to tell you more about the image search part of it. Google has claimed that it is close to perfecting a technology which will do to digital images online, what its PageRank did to web pages.
As Reported by the New York Times, On Thursday at the International World Wide Web Conference in Beijing, two Google scientists presented a paper describing what the researchers call VisualRank, an algorithm for blending image-recognition software methods with techniques for weighting and ranking images that look most similar.
Google’s breakthrough uses the “wisdom of the crowd” and contextual signals to rank the relevancy of images. VisualRank does not improve on a search engine’s ability to identify people or determine activities in a photo. The biggest benefits will be reduction of duplicate image content in search results and reduction of “image spam” or inappropriately tagged photos.
Image search at the major search engines today largely relies on looking at words that are used around images — on the pages that host them, in image file names and in ALT text associated with them. No real image recognition is done by any of the majors. Search for “apples,” and they haven’t actually somehow scanned the images itself to “see” if they contain pictures of apples.
“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, who made the presentation with Yushi Jing, another Google researcher.
The company said that in its research it had concentrated on the 2,000 most popular product queries on Google’s product search, words such as iPod, Xbox and Zune. It then sorted the Top 10 images both from its ranking system and the standard Google Image Search results. With a team of 150 Google employees, it created a scoring system for image “relevance”. The researchers said the retrieval returned 83% less irrelevant images. As stated above, that probably is the only identifiable benefit with respect to VisualRank.
Since the research has concentrated on products, im not sure how this mechanism will work for abstract images. I can understand search for people coming through due to face recognition technologies (Facial recognition is said to be done by making 3D models of faces spotted in images) being present but I have my doubts with respect to how well this technology will work with respect to terms such as ‘lost’ or ‘in the night’ – it may or may not make all search terms relevant.
2 other companies have tried to innovate with Visual Search. 1 is Polar Rose – which I was not too impressed by. The company has browser plugins and hopes to convince companies to embed its technology. There is also Riya’s Like.com, which attempts to recognise fashion products (a brown pair of shoes etc.) and directs the user to vendors online.
Riya is quite unimpressive as well. It requires a lot on behalf of the user. Further, it looks like the team has manually tagged products from various vendors and it presents them to the user when a search query is entered. It’s hardly imaginative.
We are yet to see an image search engine where a user can upload a picture and get relevant results related to that picture through the process of visual mapping.
Loading ...
Leave a Reply