Google Image Swirl 'explore visual and semantic similar images'

Google released a new Labs feature Google Image Swirl, which organizes image search results based on their visual and semantic similarities and presents them in an intuitive exploratory interface. Image Swirl currently works for more than 200,000 queries and all available queries will auto-complete as you type in search box. “Once you find a group […]

Google released a new Labs feature Google Image Swirl, which organizes image search results based on their visual and semantic similarities and presents them in an intuitive exploratory interface. Image Swirl currently works for more than 200,000 queries and all available queries will auto-complete as you type in search box. “Once you find a group of images you're interested in, you can click on thumbnail and a cluster of images will “swirl” into view. You can then further explore additional sub-groups within any cluster. Image Swirl expands on technologies developed for Similar Images and Picasa Face Recognition to discern how images should be grouped together and build hierarchies out of these groups. Each thumbnail on initial results page represents an algorithmically-determined representative group of images with similar appearance and meaning. These aren’t just most relevant images — they’re most relevant groups of images,” explains Google. Here’s an example of [washington] query:

Visit: Google Image Swirl