Google Images soon to get their own Page Rankings

This appeared in The Age Newspaper in Australia

Google algorithm improves image search


Google researchers said they had a software technology intended to do for digital images on the web what the company's original PageRank software did for searches of web pages.

Last week, at the International World Wide Web Conference in Beijing, two Google scientists presented a paper describing what the researchers called VisualRank, an algorithm for blending image-recognition software methods with techniques for weighting and ranking images that look most similar.

Although image search had become popular on commercial search engines, results were usually generated by using cues from the text that is associated with each image.

Image analysis remained a largely unsolved problem in computer science, the researchers said.

So while progress had been made in automatic face detection in images, finding other objects such as mountains or tea pots, which were instantly recognisable to humans, had lagged.

"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's expertise in creating vast graphs that weigh "nodes", or web pages, based on their "authority" could be applied to images that were the most representative of a particular query, he said.

The research paper focused on a subset of images the giant search engine had catalogued because of the tremendous computing costs required to analyse and compare digital images. To do this for all of the images indexed by the search engine would be impractical, the researchers said. Google did not disclose how many images it had catalogued.

The company said that in its research it had concentrated on the 2000 most popular product queries on Google's product search, words such as iPod, Xbox and Zune. It then sorted the top 10 images 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 per cent less irrelevant images.

The New York Times