A hierarchical field framework for unified context-based classification
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15505499) , 1284
- https://doi.org/10.1109/iccv.2005.9
Abstract
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional field that allows one to capture arbitrary observation-dependent label interactions. The proposed framework has two main advantages. First, it encodes both the short-range interactions (e.g., pixelwise label smoothing) as well as the long-range interactions (e.g., relative configurations of objects or regions) in a tractable manner. Second, the formulation is general enough to be applied to different domains ranging from pixelwise image labeling to contextual object detection. The parameters of the model are learned using a sequential maximum-likelihood approximation. The benefits of the proposed framework are demonstrated on four different datasets and comparison results are presentedKeywords
This publication has 6 references indexed in Scilit:
- Contextual Recognition of Hand-Drawn Diagrams with Conditional Random FieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Probabilistic spatial context models for scene content understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An observation-constrained generative approach for probabilistic classification of image regionsImage and Vision Computing, 2003
- Combining belief networks and neural networks for scene segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Sonar image segmentation using an unsupervised hierarchical MRF modelIEEE Transactions on Image Processing, 2000
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984