A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data

Xavier Ceamanos (1) , Bjorn Waske (2) , Jon Atli Benediktsson (3) , Jocelyn Chanussot (4) , Mathieu Fauvel (5) , Johannes Sveinsson (3)

1 LPG - Laboratoire de Planétologie de Grenoble
2 Universität Bonn = University of Bonn
3 University of Iceland [Reykjavik]
4 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
5 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems

Classification of hyperspectral data using a classifier ensemble that is based on support vector machines (SVMs) are addressed. First, the hyperspectral data set is decomposed into a few data sources according to the similarity of the spectral bands. Then, each source is processed separately by performing classification based on SVM. Finally, all outputs are used as input for final decision fusion performed by an additional SVM classifier. Results of the experiments underline how the proposed SVM fusion ensemble outperforms a standard SVM classifier in terms of overall and class accuracies, the improvement being irrespective of the size of the training sample set. The definition of the data sources resulting from the original data set is also studied.

Mots clés: classification of remote sensing data; support vector machines; hyperspectral data; decision fusion

Domaines: Traitement des images [eess.IV]

Xavier Ceamanos, Bjorn Waske, Jon Atli Benediktsson, Jocelyn Chanussot, Mathieu Fauvel, et al.. A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data. International Journal of Image and Data Fusion, 2010, 1 (4), pp.293-307. ⟨10.1080/19479832.2010.485935⟩. ⟨hal-00578897⟩