| |
|
|
| project results: |
Context-aware Classification
Arne Kreutzmann, Kasim Terzić, Bernd Neumann
Cognitive Systems Laboratory, Department of Informatics
University of Hamburg
October, 2009
 |
|
Appearance-based classification is a difficult task in many domains due to ambiguous evidence. Knowledge about the relationships between objects in the scene can help to resolve this problem. We have developed a new probabilistic classification framework based on the cooperation of decision trees and Bayesian Compositional Hierarchies, and have shown that introducing contextual knowledge in the form of dynamic priors significantly improves classification performance in the facade domain. For example, in storey images, balcony doors and windows could be much better distinguished once a probabilistic context was established.
|
References
| [1] |
Kreutzmann, A., Terzić, K. & Neumann, B.
Context-aware Classification for Incremental Scene Interpretation
to appear in: Proc. Workshop on Use of Context in Vision Processing
2009
[pdf]
|
|
|
