Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

UC San Diego researchers give computers 'common sense'

22.10.2007
Using a little-known Google Labs widget, computer scientists from UC San Diego and UCLA have brought common sense to an automated image labeling system. This common sense is the ability to use context to help identify objects in photographs.

For example, if a conventional automated object identifier has labeled a person, a tennis racket, a tennis court and a lemon in a photo, the new post-processing context check will re-label the lemon as a tennis ball.

“We think our paper is the first to bring external semantic context to the problem of object recognition,” said computer science professor Serge Belongie from UC San Diego.

The researchers show that the Google Labs tool called Google Sets can be used to provide external contextual information to automated object identifiers. The paper will be presented on Thursday 18 October 2007 at ICCV 2007 – the 11th IEEE International Conference on Computer Vision in Rio de Janeiro, Brazil.

Google Sets generates lists of related items or objects from just a few examples. If you type in John, Paul and George, it will return the words Ringo, Beatles and John Lennon. If you type “neon” and “argon” it will give you the rest of the noble gasses.

“In some ways, Google Sets is a proxy for common sense. In our paper, we showed that you can use this common sense to provide contextual information that improves the accuracy of automated image labeling systems,” said Belongie.

The image labeling system is a three step process. First, an automated system splits the image up into different regions through the process of image segmentation. In the photo above, image segmentation separates the person, the court, the racket and the yellow sphere.

Next, an automated system provides a ranked list of probable labels for each of these image regions.

Finally, the system adds a dose of context by processing all the different possible combinations of labels within the image and maximizing the contextual agreement among the labeled objects within each picture.

It is during this step that Google Sets can be used as a source of context that helps the system turn a lemon into a tennis ball. In this case, these “semantic context constraints” helped the system disambiguate between visually similar objects.

In another example, the researchers show that an object originally labeled as a cow is (correctly) re-labeled as a boat when the other objects in the image – sky, tree, building and water – are considered during the post-processing context step. In this case, the semantic context constraints helped to correct an entirely wrong image label. The context information came from the co-occurrence of object labels in the training sets rather than from Google Sets.

The computer scientists also highlight other advances they bring to automated object identification. First, instead of doing just one image segmentation, the researchers generated a collection of image segmentations and put together a shortlist of stable image segmentations. This increases the accuracy of the segmentation process and provides an implicit shape description for each of the image regions.

Second, the researchers ran their object categorization model on each of the segmentations, rather than on individual pixels. This dramatically reduced the computational demands on the object categorization model.

In the two sets of images that the researchers tested, the categorization results improved considerably with inclusion of context. For one image dataset, the average categorization accuracy increased more than 10 percent using the semantic context provided by Google Sets. In a second dataset, the average categorization accuracy improved by about 2 percent using the semantic context provided by Google Sets. The improvements were higher when the researchers gleaned context information from data on co-occurrence of object labels in the training data set for the object identifier.

Right now, the researchers are exploring ways to extend context beyond the presence of objects in the same image. For example, they want to make explicit use of absolute and relative geometric relationships between objects in an image – such as “above” or “inside” relationships. This would mean that if a person were sitting on top of an animal, the system would consider the animal to be more likely a horse than a dog.

Paper Information:

“Objects in Context,” by Andrew Rabinovich, Carolina Galleguillos, Eric Wiewiora and Serge Belongie from the Department of Computer Science and Engineering at the UCSD Jacobs School of Engineering. Andrea Vedaldi from the Department of Computer Science, UCLA.

Read that paper at: http://www.cs.ucsd.edu/~sjb/iccv2007a.pdf
The paper will be presented on Thursday 18 October 2007 at ICCV 2007 – the 11th IEEE International Conference on Computer Vision in Rio de Janeiro, Brazil.
Funders:
National Science Foundation (NSF)
Afred P. Sloan Research Fellowship
Air Force Office of Scientific Research (AFOSR)
Office of Naval Research (ONR)
Author contact:
Serge Belongie
sjb@cs.ucsd.edu
Media contact:
Daniel Kane
dbkane@ucsd.edu
858-534-3262

Daniel Kane | EurekAlert!
Further information:
http://www.jacobsschool.ucsd.edu/news/news_releases/release.sfe?id=698
http://www.cs.ucsd.edu/~sjb/iccv2007a.pdf
http://www.ucsd.edu

More articles from Information Technology:

nachricht Putting food-safety detection in the hands of consumers
15.11.2018 | Massachusetts Institute of Technology

nachricht Next stop Morocco: EU partners test innovative space robotics technologies in the Sahara desert
09.11.2018 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: UNH scientists help provide first-ever views of elusive energy explosion

Researchers at the University of New Hampshire have captured a difficult-to-view singular event involving "magnetic reconnection"--the process by which sparse particles and energy around Earth collide producing a quick but mighty explosion--in the Earth's magnetotail, the magnetic environment that trails behind the planet.

Magnetic reconnection has remained a bit of a mystery to scientists. They know it exists and have documented the effects that the energy explosions can...

Im Focus: A Chip with Blood Vessels

Biochips have been developed at TU Wien (Vienna), on which tissue can be produced and examined. This allows supplying the tissue with different substances in a very controlled way.

Cultivating human cells in the Petri dish is not a big challenge today. Producing artificial tissue, however, permeated by fine blood vessels, is a much more...

Im Focus: A Leap Into Quantum Technology

Faster and secure data communication: This is the goal of a new joint project involving physicists from the University of Würzburg. The German Federal Ministry of Education and Research funds the project with 14.8 million euro.

In our digital world data security and secure communication are becoming more and more important. Quantum communication is a promising approach to achieve...

Im Focus: Research icebreaker Polarstern begins the Antarctic season

What does it look like below the ice shelf of the calved massive iceberg A68?

On Saturday, 10 November 2018, the research icebreaker Polarstern will leave its homeport of Bremerhaven, bound for Cape Town, South Africa.

Im Focus: Penn engineers develop ultrathin, ultralight 'nanocardboard'

When choosing materials to make something, trade-offs need to be made between a host of properties, such as thickness, stiffness and weight. Depending on the application in question, finding just the right balance is the difference between success and failure

Now, a team of Penn Engineers has demonstrated a new material they call "nanocardboard," an ultrathin equivalent of corrugated paper cardboard. A square...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

“3rd Conference on Laser Polishing – LaP 2018” Attracts International Experts and Users

09.11.2018 | Event News

On the brain’s ability to find the right direction

06.11.2018 | Event News

European Space Talks: Weltraumschrott – eine Gefahr für die Gesellschaft?

23.10.2018 | Event News

 
Latest News

Purdue cancer identity technology makes it easier to find a tumor's 'address'

16.11.2018 | Health and Medicine

Good preparation is half the digestion

16.11.2018 | Life Sciences

Microscope measures muscle weakness

16.11.2018 | Life Sciences

VideoLinks
Science & Research
Overview of more VideoLinks >>>