Featured Research

from universities, journals, and other organizations

Computer searches web 24/7 to analyze images and teach itself common sense

Date:
November 20, 2013
Source:
Carnegie Mellon University
Summary:
A computer program called the Never Ending Image Learner (NEIL) is running 24 hours a day searching the Internet for images, doing its best to understand them on its own and, as it builds a growing visual database, gathering common sense on a massive scale.

A computer program called the Never Ending Image Learner (NEIL) is running 24 hours a day at Carnegie Mellon University, searching the Web for images, doing its best to understand them on its own and, as it builds a growing visual database, gathering common sense on a massive scale.
Credit: SSilver / Fotolia

A computer program called the Never Ending Image Learner (NEIL) is running 24 hours a day at Carnegie Mellon University, searching the Web for images, doing its best to understand them on its own and, as it builds a growing visual database, gathering common sense on a massive scale.

NEIL leverages recent advances in computer vision that enable computer programs to identify and label objects in images, to characterize scenes and to recognize attributes, such as colors, lighting and materials, all with a minimum of human supervision. In turn, the data it generates will further enhance the ability of computers to understand the visual world.

But NEIL also makes associations between these things to obtain common sense information that people just seem to know without ever saying -- that cars often are found on roads, that buildings tend to be vertical and that ducks look sort of like geese. Based on text references, it might seem that the color 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."

A computer cluster has been running the NEIL program since late July and already has analyzed 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.

The public can now view NEIL's findings at the project website, http://www.neil-kb.com.

The research team, including Xinlei Chen, a Ph.D. student in CMU's Language Technologies Institute, and Abhinav Shrivastava, a Ph.D. student in robotics, will present its findings on Dec. 4 at the IEEE International Conference on Computer Vision in Sydney, Australia.

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 labeled and catalogued.

"What we have learned in the last 5-10 years of computer vision research is that the more data you have, the better computer vision becomes," Gupta said.

Some projects, such as ImageNet and Visipedia, have tried to compile this structured data with human assistance. But the scale of the Internet is so vast -- Facebook alone holds more than 200 billion images -- that the only hope to analyze it all is to teach computers to do it largely by themselves.

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 color.

"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 analyze. 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 landlubbing 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 motorized, 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.


Story Source:

The above story is based on materials provided by Carnegie Mellon University. Note: Materials may be edited for content and length.


Cite This Page:

Carnegie Mellon University. "Computer searches web 24/7 to analyze images and teach itself common sense." ScienceDaily. ScienceDaily, 20 November 2013. <www.sciencedaily.com/releases/2013/11/131120111956.htm>.
Carnegie Mellon University. (2013, November 20). Computer searches web 24/7 to analyze images and teach itself common sense. ScienceDaily. Retrieved July 29, 2014 from www.sciencedaily.com/releases/2013/11/131120111956.htm
Carnegie Mellon University. "Computer searches web 24/7 to analyze images and teach itself common sense." ScienceDaily. www.sciencedaily.com/releases/2013/11/131120111956.htm (accessed July 29, 2014).

Share This




More Computers & Math News

Tuesday, July 29, 2014

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

Teen's Phone Ignites Under Her Pillow; How Real Is The Risk?

Teen's Phone Ignites Under Her Pillow; How Real Is The Risk?

Newsy (July 28, 2014) A Texas teen's Samsung phone apparently ignited while she slept, but what was the real problem here? Video provided by Newsy
Powered by NewsLook.com
Google's Next Frontier: The Human Body

Google's Next Frontier: The Human Body

Newsy (July 27, 2014) Google is collecting genetic and molecular information to paint a picture of the perfectly healthy human. Video provided by Newsy
Powered by NewsLook.com
Cellphone Unlocking Bill Clears U.S. House, Heads to Obama

Cellphone Unlocking Bill Clears U.S. House, Heads to Obama

Reuters - US Online Video (July 27, 2014) Congress gets rid of pesky law that made it illegal to "unlock" mobile phones without permission, giving consumers the option to use the same phone on a competitor's wireless network. Mana Rabiee reports. Video provided by Reuters
Powered by NewsLook.com
Congress OKs Unlocking Phones From Carriers

Congress OKs Unlocking Phones From Carriers

Newsy (July 26, 2014) A bill legalizing "unlocking," or untethering a phone from its default wireless carrier, has passed Congress and is expected to be signed into law. Video provided by Newsy
Powered by NewsLook.com

Search ScienceDaily

Number of stories in archives: 140,361

Find with keyword(s):
Enter a keyword or phrase to search ScienceDaily for related topics and research stories.

Save/Print:
Share:

Breaking News:
from the past week

In Other News

... from NewsDaily.com

Science News

Health News

Environment News

Technology News



Save/Print:
Share:

Free Subscriptions


Get the latest science news with ScienceDaily's free email newsletters, updated daily and weekly. Or view hourly updated newsfeeds in your RSS reader:

Get Social & Mobile


Keep up to date with the latest news from ScienceDaily via social networks and mobile apps:

Have Feedback?


Tell us what you think of ScienceDaily -- we welcome both positive and negative comments. Have any problems using the site? Questions?
Mobile: iPhone Android Web
Follow: Facebook Twitter Google+
Subscribe: RSS Feeds Email Newsletters
Latest Headlines Health & Medicine Mind & Brain Space & Time Matter & Energy Computers & Math Plants & Animals Earth & Climate Fossils & Ruins