Text Size
- Home
-
News
Advanced computing news from Communications of the ACM, other ACM resources, and from around the Web.
- Blogs
- Opinion
-
Browse by Subject
Recent articles from Communications organized into categories that encompass the broad scope of computing.
-
Magazine Archive
-
Careers
Jump-start your career with information on trends, opportunities and jobs – in both industry and academia.
- ACM Resources
-
Subscribe
Receive the benefits of ACM membership with a subscription to its flagship publication, Communications of the ACM.
This Article
ACM TechNews
Seeing Things
![[article image]](/system/assets/0000/1675/101609_CeLiu_Object_Recognition.large.jpg?1255714842&1255714840 "object recognition image")
MIT's object recognition system will label objects in a new image if they map onto an image that has been previously outlined and labeled.
Courtesy of Ce Liu / MIT
Massachusetts Institute of Technology (MIT) professor Antonio Torralba and students from the school's Computer Science and Artificial Intelligence Lab (CSAIL) say they have developed an object recognition system that requires no training and can identify objects at least as well as and any other available program.
The CSAIL system uses a modified version of a motion estimation algorithm. Consecutive frames of video normally change very little, so data compression schemes often store the unchanging elements of a scene once and only update the positions of moving objects, with motion estimation algorithms determining what objects move.
The MIT system treats unrelated images as if they were consecutive frames in a video sequence. When the modified motion estimation algorithm attempts to determine what objects have "moved" between one image and the next, the system can identify objects of the same type.
"It's a real commonsense solution to a fundamental problem in computer vision," says University of Central Florida professor Marshall Tappen. "The results are great and better than you can get with much more complicated methods."
From MIT News
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA 
Sign In To Comment On This Article
Create A Web Account
If you are an ACM member, Communications subscriber, Digital Library subscriber, or use your institution's subscription, please set up a web account to access comments, premium content and additional site features.
If you are a SIG member or member of the general public, you may set up a web account to comment on free articles and sign up for email alerts.
Tools For Readers
Related ACM Resources
Conferences:
- WICON 2010: International Wireless Internet Conference - March 1, 2010 – March 3, 2010; Singapore
Books:
- Learning Ruby - Michael Fitzgerald
Courses:
- Working with Type Metadata in the Microsoft .NET Framework 2.0 - In this 2-hour course you will learn about using reflection to work with type metadata in the Microsoft .NET Framework 2.0. Topics range from accessing …
About Communications |
Join ACM 
|
Renew |
Subscribe |
Sign In |
For Authors |
For Advertisers |
Privacy |
Site Map |
Help |
Contact Us
Copyright © 2009 by the ACM. All rights reserved.