A Google Prototype for a Precision Image Search

SAN FRANCISCO — Google researchers say they have 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.

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.

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

Despite decades of effort, image analysis remains a largely unsolved problem in computer science, the researchers said. For example, while progress has been made in automatic face detection in images, finding other objects such as mountains or tea pots, which are instantly recognizable to humans, has 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” can be applied to images that are the most representative of a particular query, he said.

The research paper, “PageRank for Product Image Search,” is focused on a subset of the images that the giant search engine has cataloged because of the tremendous computing costs required to analyze and compare digital images. To do this for all of the images indexed by the search engine would be impractical, the researchers said. Google does not disclose how many images it has cataloged, but it asserts that its Google Image Search is the “most comprehensive image search on the Web.”

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 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 percent less irrelevant images.

Google is not the first into the visual product search category. Riya, a Silicon Valley start-up, introduced Like.com in 2006. The service, which refers users to shopping sites, makes it possible for a Web shopper to select a particular visual attribute, such as a certain style of brown shoes or a style of buckle, and then be presented with similar products available from competing Web merchants.

Rather than relying on a text query, the service focuses on the ability to match shapes or objects that might be hard to describe in writing, said Munjal Shah, the chief executive of Riya.

“I think what they’re trying to accomplish is largely impossible,” he said. “Our belief is, there is not large-scale solutions.”

Mr. Shah said there had been a number of technology demonstrations by Google Labs researchers, such as a project in 2005 that used machine learning techniques to recognize the gender of a person in an image. However, the company has been slow to deploy its research, he said.

If you need Internet Marketing or SEO advice, contact me at http://www.annatulchinsky.com

Yahoo Goes to Bed with Google

Another shot has been fired in the bitter battle between Microsoft and Yahoo.

The Internet company plans to announce Wednesday afternoon that it will begin a test advertising partnership with Google, people briefed on the plan told DealBook. In the experiment, expected to last for two weeks and applying only to users in the United States, Yahoo will display Google-provided ads alongside its own search results, these people said.

The move is the latest salvo in the two-month battle for control of Yahoo, as the ailing Internet pioneer seeks to thwart Microsoft’s bid – or at least force the software giant to raise its $42 billion price.

Depending on the results of the experiment, Yahoo hopes that it may be able to use it as proof that it can generate additional revenue that would justify a higher bid.

In recent months, Yahoo has discussed possible partnerships or combinations with Google, Time Warner’s AOL and the News Corporation in attempts to fend off Microsoft. Some of those conversations are continuing, people familiar with the matter previously told The New York Times.

Google has long generated far more revenue for every search than competitors like Yahoo and Microsoft. Last year, Yahoo unveiled a new search advertising system, called Panama, which was intended to close the gap with Google. While the system has helped bolster Yahoo’s search revenues, it is not as effective as Google’s.

Some investors have urged Yahoo to outsource its search and search advertising system to Google for years, as it could help Yahoo increase revenues and cut costs. Yahoo executives, however, have resisted the move, saying that search was an essential piece of the company’s business.

After Microsoft made its offer, Eric Schmidt, Google’s chief executive, called his Yahoo counterpart, Jerry Yang, to offer his help in fending off the Microsoft bid. A search or search advertising partnership has been an important part of their discussion, according to people familiar with the situation. Mr. Yang and Yahoo president Susan Decker visited Google in the past two weeks, said a person briefed on their visit.

While the test is intended to show how much Yahoo could earn from such a partnership, legal experts have warned that a broader search or search advertising pact with Google could pose antitrust issues, as it would expand Google’s already dominant position in those businesses.

Does this mean that Google may actually buy Yahoo in the future?