Skip to Main content Skip to Navigation
Conference papers

Unsupervised Classifier Selection Approach for Hyperspectral Image Classification

Bharath Bhushan Damodaran 1 Nicolas Courty 1 Sébastien Lefèvre 1
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Generating accurate and robust classification maps from hy-perspectral imagery (HSI) depends on the users choice of the classifiers and input data sources. Choosing the appropriate classifier for a problem at hand is a tedious task. Multiple classifier system (MCS) combines the relative merits of the various classifiers to generate robust classification maps. However, the presence of inaccurate classifiers may degrade the classification performance of MCS. In this paper, we propose a unsupervised classifier selection strategy to select an appropriate subset of accurate classifiers for the multiple clas-sifier combination from a large pool of classifiers. The experimental results with two HSI show that the proposed classifier selection method overcomes the impact of inaccurate classi-fiers and increases the classification accuracy significantly.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01320020
Contributor : Sébastien Lefèvre <>
Submitted on : Wednesday, November 13, 2019 - 6:41:05 PM
Last modification on : Thursday, April 2, 2020 - 1:54:32 AM

File

igarss2016selection.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01320020, version 1

Citation

Bharath Bhushan Damodaran, Nicolas Courty, Sébastien Lefèvre. Unsupervised Classifier Selection Approach for Hyperspectral Image Classification. IEEE International Geosciences and Remote Sensing Symposium (IGARSS), 2016, Beijing, China. ⟨hal-01320020⟩

Share

Metrics

Record views

1128

Files downloads

94