Path: EDN Asia >> News Centre >> Computing/Peripherals >> NEIL program studies images with minimal human supervision
Computing/Peripherals Share print

NEIL program studies images with minimal human supervision

25 Nov 2013

Share this page with your friends

Carnegie Mellon University researchers in July launched a computer cluster that runs a program called the never ending image learner (NEIL), which is designed to scan and understand images that it retrieves from the Internet. The 24/7 NEIL program builds on computer vision technology advancements that enable computer programs to recognise objects, scenes, attributes, colours, lighting and materials with minimum human supervision. A visual database to improve computers' "common sense" is being built as a result of this initiative. NEIL's findings, which can be accessed at www.neil-kb.com, will be presented at the IEEE International Conference on Computer Vision in Sydney, Australia.

Aside from collection and recognition, NEIL also has the ability to make associations between different images to obtain common sense information that people just seem to know without ever saying. For instance, text references would indicate that the colour associated with sheep is black, but people—and NEIL—nevertheless know that sheep typically are white.

"Images are the best way to learn visual properties," said Abhinav Gupta, assistant research professor in Carnegie Mellon's Robotics Institute. "Images also include a lot of common sense information about the world. People learn this by themselves and, with NEIL, we hope that computers will do so as well."

NEIL has so far analysed three million images, identifying 1,500 types of objects in half a million images and 1,200 types of scenes in hundreds of thousands of images. It has connected the dots to learn 2,500 associations from thousands of instances. One motivation for the NEIL project is to create the world's largest visual structured knowledge base, where objects, scenes, actions, attributes and contextual relationships are labelled and catalogued.

Researcher Abhinav Shrivastava said NEIL can sometimes make erroneous assumptions that compound mistakes, so people need to be part of the process. A Google Image search, for instance, might convince NEIL that "pink" is just the name of a singer, rather than a colour.

"People don't always know how or what to teach computers," he observed. "But humans are good at telling computers when they are wrong."

People also tell NEIL what categories of objects, scenes, etc., to search and analyse. But sometimes, what NEIL finds can surprise even the researchers. It can be anticipated, for instance, that a search for "apple" might return images of fruit as well as laptop computers. But Gupta and his team had no idea that a search for F-18 would identify not only images of a fighter jet, but also of F18-class catamarans.

As its search proceeds, NEIL develops subcategories of objects—tricycles can be for kids, for adults and can be motorised, or cars come in a variety of brands and models. And it begins to notice associations—that zebras tend to be found in savannahs, for instance, and that stock trading floors are typically crowded.

NEIL is computationally intensive, the research team noted. The program runs on two clusters of computers that include 200 processing cores.




Want to more of this to be delivered to you for FREE?

Subscribe to EDN Asia alerts and receive the latest design ideas and product news in your inbox.

Got to make sure you're not a robot. Please enter the code displayed on the right.

Time to activate your subscription - it's easy!

We have sent an activate request to your registerd e-email. Simply click on the link to activate your subscription.

We're doing this to protect your privacy and ensure you successfully receive your e-mail alerts.


Add New Comment
Visitor (To avoid code verification, simply login or register with us. It is fast and free!)
*Verify code:
Tech Impact

Regional Roundup
Control this smart glass with the blink of an eye
K-Glass 2 detects users' eye movements to point the cursor to recognise computer icons or objects in the Internet, and uses winks for commands. The researchers call this interface the "i-Mouse."

GlobalFoundries extends grants to Singapore students
ARM, Tencent Games team up to improve mobile gaming


News | Products | Design Features | Regional Roundup | Tech Impact