Google has launched Google Image Swirl, a new image discovery tool that visually clusters similar images. It automatically organizes image search results into groups and sub-groups.

Swirl uses algorithms, metadata, and facial recognition software to distinguish between structures, places, people, and even time of day in digital images. For example, if you search for “New Delhi,” you will get sets of New Delhi state maps, and various scenery of the state. As you drill down further into the results, you get to see more tightly refined sets of images based on what you choose.

Clicking on any of the subgroups opens a window into additional “sub-clusters” of pictures categorized by factors such as angle, time of day, and whether an image is a close-up or a panorama.

We can play with Image Swirl at Google Labs.