Ensemble Strategies for Classifying Hyperspectral Remote Sensing Data

Authors:
Xavier Ceamanos;Björn Waske;Jón Atli Benediktsson;Jocelyn Chanussot;Johannes R. Sveinsson
Affiliations:
GIPSA-LAB, Signal & Image Department, Grenoble Institute of Technology, INPG, Saint Martin d'Hèèères, France 38402;Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland 107;Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland 107;GIPSA-LAB, Signal & Image Department, Grenoble Institute of Technology, INPG, Saint Martin d'Hèèères, France 38402;Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland 107
Venue:
MCS '09 Proceedings of the 8th International Workshop on Multiple Classifier Systems
Year:
2009

Citing 7
Cited 0

Original Contribution: Stacked generalization

Neural Networks
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Maximum Entropy Markov Models for Information Extraction and Segmentation

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Machine Learning for Sequential Data: A Review

Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Global Training of Document Processing Systems Using Graph Transformer Networks

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Training conditional random fields via gradient tree boosting

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Stacked sequential learning

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The classification of hyperspectral imagery, using multiple classifier systems is discussed and an SVM-based ensemble is introduced. The data set is separated into separate feature subsets using the correlation between the different spectral bands as a criterion. Afterwards, each source is classified separately by an SVM classifier. Finally, the different outputs are used as inputs for final decision fusion that is based on an additional SVM classifier. The results using the proposed strategy are compared to classification results achieved by a single SVM and other well known classifier ensembles, such as random forests, boosting and bagging.