Google has announced some significant changes to its Image Search tool. First launched in 2001 the image database has grown from 250 million images to over 10 billion images now. Over this time the search tool has been enhanced to improve the search results and to include different search filters, such as images of clip art, line drawings, faces and even different colour themes.

In addition, Google's sophisticated computer vision technology powers the “Similar images” tool to recognise similar patterns and images or “Similar colors” refinement which returns images with the core image area containing the similar colour content. However, with the developments going on at Microsoft's Bing search engine, Google also has to keep up with, or ahead of, the game, and is now making further enhancements to the image search results.

The most obvious change is a new tiled layout which removes the content around each image and makes it easier to view lots of images at once. There's also instant scrolling between pages, with up to 1,000 images, all in one scrolling page. The thumbnail previews on the results page are also larger and a hover pane now appears when users mouse over an image, providing a larger preview and more information about the image.

Once users click on an image, they're taken to a new landing page that displays a large image in context, with the website it’s hosted on visible right behind it. By clicking anywhere outside the image users are taken right onto the original page where the image was located.

Google has also announced a new ad format for PPC advertisers, called Image Search Ads. These ads appear only on Google Images and let advertisers include a thumbnail image alongside the standard lines of text - a good option for companies selling products that benefit from a visual approach.

A recent article by The New York Times reports on a research paper presented at the International World Wide Web Conference in Beijing by 2 Google scientists, which described the development of 'VisualRank' by the search engine. This is the prototype algorithm that combines image-recognition software techniques with the methods for weighting and ranking images that look most similar. Described as the equivalent of Google's main PageRank system adapted for digital images, it's being seen as potentially a big step forward for the quality of image searching on the web.

Image search has long been one of the most popular 'vertical' search options on the main search engines and more recently Google, Ask and the others have been 'blending' image results into the main search results list, when relevant, thereby giving image search results far more exposure to mainstream searchers. Up until now, image results are usually generated from information in the file name and surrounding page content, but Google - and others - are working on ways to analyse image form and shape similarities.

The article says that Google has been working on a sample of around 2,000 of the most popular product queries from Google’s product search - so items such as iPod and Xbox - and then sorting the top 10 images both from its main ranking system and the standard Google image search results. Using a team of 150 Google employees, the researchers then created a scoring system for image “relevance”, which is being referred to as VisualRank. The outcome of this development, according to the researchers, was to retrieve new image results that were 83% less irrelevant.