Problem-Based Band Selection for hyperspectral images - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Problem-Based Band Selection for hyperspectral images


This paper addresses the band selection of a hyperspectral image. Considering a binary classification, we devise a method to choose the more discriminating bands for the separation of the two classes involved, by using a simple algorithm: single-layer neural network. After that, the most discrimi-native bands are selected, and the resulting reduced data set is used in a more powerful classifier, namely, stacked de-noising autoencoder. Besides its simplicity, the advantage of this method is that the selection of features is made by an algorithm similar to the classifier to be used, and not focused only on the separability measures of the data set. Results indicate the decrease of overfitting for the reduced data set, when compared to the full data architecture.
Fichier principal
Vignette du fichier
mateus_igarss.pdf (3.08 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01678876 , version 1 (09-01-2018)


  • HAL Id : hal-01678876 , version 1


Mateus Habermann, Vincent Frémont, Elcio Hideiti Shiguemori. Problem-Based Band Selection for hyperspectral images. IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2017), Jul 2017, Fort Worth, United States. pp.1800-1803. ⟨hal-01678876⟩
62 View
61 Download


Gmail Facebook Twitter LinkedIn More