Look at TinEye, The New Image Search Engine
Today Idée Inc. announced the launch of TinEye, their image search engine, a search engine touted to do for images what Google did for text. Just as you are familiar with entering text in Google to find web pages that contain that text, using TinEye, you enter an image to find pages where that particular image (and modified versions of it) appears.
Tineye was founded by Idée Inc., a company that develops advanced image identification and visual search software. The service provides clients with reports of where their images and videos have been used, allowing photo wire agencies, stock photography firms and entertainment and media companies to recover lost revenues by identifying billable image uses or infringements. Tineye currently boasts a library of nearly half a billion images in its database. Potential users may request an invite to be involved in the testing process, though the beta is currently at capacity.
Available in a closed beta at tineye.com, the new image search engine showcases Idée’s image index and search capabilities and introduces the world’s first image identification based internet search engine.
“Today our new image identification based search engine allows users to search over 487 million images in mere seconds,” said Leila Boujnane, Idée CEO and co-founder, “but that is just the beginning. Our unparalleled image identification technology will enable millions of users worldwide to search for images like never before.”
Instead of using tags or keywords as you would do with existing image search engines, TinEye allows you to use an actual photo, or an image from the web, to find almost instantly where that image has appeared on websites from all over the internet.
Today users can search close to half a billion images from an ever-expanding index of web images. TinEye is regularly crawling the web and indexing images based on their individual digital signatures or ‘fingerprints’. Unlike any other search engine, when TinEye finds an image, it looks at the pixels in the image. Even if the image has been altered through edits including crops, colour adjustments, objects added or removed, or even skews, TinEye can identify it.
Thanks again to Rafi for this post!
