Google image search gets a 'swirl'

Nov 17, 2009
Google Labs on Tuesday brought more focus to finding pictures online, adding a "Swirl" tool that automatically groups similar images into categories presented on results pages.

Google Labs on Tuesday brought more focus to finding pictures online, adding a "Swirl" tool that automatically groups similar images into categories presented on results pages.

"What Image Swirl does is it really organizes automatically image search results into groups and sub-groups," product manager Aparna Chennapragada told AFP.

"It's not just the face, the color, the visual features of the images; we look inside the image and ask how they relate to each other on a pixel level."

Swirl uses algorithms, metadata, and facial recognition software to distinguish between structures, places, people, and even time of day in digital images.

For example, an Image Swirl search using the keyword "Washington" triggers a results page with pictures packed into subsets including the White House, former president George Washington, and actor Denzel Washington.

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.

Online image search has traditionally delivered results pages lined with thumbnail pictures that people sift through individually.

"As humans we can easily tell which images should be grouped together by looking at them," sad Google software engineer Yushi Jing, who worked on Image Swirl underlying technology.

"The real question is can we train computer algorithms to identify common features in images and then categorize them. It's not perfect. We may have mistakes, but we hope to improve this system as we move forward."

People can dabble with Image Swirl at Google Labs. Feedback will be used to improve the tool with the ultimate objective being to one day incorporate it in the California Internet giant's public .

"We are committed to how we look at and understand and organize it for our users," Chennapragada said. "This is the holy grail of computer vision."

Google launched image search in 2001 and later added a "similar images" feature to hone-in picture hunts.

(c) 2009 AFP

Explore further: Lions Gate partners with online outfit RocketJump

add to favorites email to friend print save as pdf

Related Stories

Researchers develop new image-recognition software

May 21, 2008

It takes surprisingly few pixels of information to be able to identify the subject of an image, a team led by an MIT researcher has found. The discovery could lead to great advances in the automated identification ...

Recommended for you

Instagram photo-sharing service goes down

Apr 12, 2014

Popular photo-sharing site Instagram was not working Saturday, as frustrated users quickly turned to social network Twitter and other web sites to share their complaints.

Authors Guild asks US court to rule against Google

Apr 11, 2014

The Authors Guild says that Google Inc. is stealing business from retailers and has asked a New York federal appeals court to find that the Internet giant is violating copyright laws with its massive book digitization project.

User comments : 1

Adjust slider to filter visible comments by rank

Display comments: newest first

SmartK8
not rated yet Nov 18, 2009
It still has some pixel-related problems. Because when I tried to search for Obama, it came alright. Then I clicked a second picture in the results, to find the similar images and it found Mohammed Atta. :/ Otherwise kudos. I'm using this feature for icon search and it's the best, so far.

More news stories

Patent talk: Google sharpens contact lens vision

(Phys.org) —A report from Patent Bolt brings us one step closer to what Google may have in mind in developing smart contact lenses. According to the discussion Google is interested in the concept of contact ...

Tech giants look to skies to spread Internet

The shortest path to the Internet for some remote corners of the world may be through the skies. That is the message from US tech giants seeking to spread the online gospel to hard-to-reach regions.

Wireless industry makes anti-theft commitment

A trade group for wireless providers said Tuesday that the biggest mobile device manufacturers and carriers will soon put anti-theft tools on the gadgets to try to deter rampant smartphone theft.

ESO image: A study in scarlet

This new image from ESO's La Silla Observatory in Chile reveals a cloud of hydrogen called Gum 41. In the middle of this little-known nebula, brilliant hot young stars are giving off energetic radiation that ...

First direct observations of excitons in motion achieved

A quasiparticle called an exciton—responsible for the transfer of energy within devices such as solar cells, LEDs, and semiconductor circuits—has been understood theoretically for decades. But exciton movement within ...

Warm US West, cold East: A 4,000-year pattern

Last winter's curvy jet stream pattern brought mild temperatures to western North America and harsh cold to the East. A University of Utah-led study shows that pattern became more pronounced 4,000 years ago, ...