Using the forest to see the trees
Abstract
Recognizing objects in images is an active area of research in computer vision. In the last two decades, there has been much progress and there are already object recognition systems operating in commercial products. However, most of the algorithms for detecting objects perform an exhaustive search across all locations and scales in the image comparing local image regions with an object model. That approach ignores the semantic structure of scenes and tries to solve the recognition problem by brute force. In the real world, objects tend to covary with other objects, providing a rich collection of contextual associations. These contextual associations can be used to reduce the search space by looking only in places in which the object is expected to be; this also increases performance, by rejecting patterns that look like the target but appear in unlikely places.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Mar 01, 2010
- Source ID
- 10.1145/1666420.1666446
Entities
People
- A. Torralba
- K. P. Murphy
- William T. Freeman
Organizations
- Division of Information and Intelligent Systems
- Massachusetts Institute of Technology
- National Geospatial-Intelligence Agency
- Office of Naval Research
- University of British Columbia