Unsupervised Band Selection in Hyperspectral Images using Autoencoder - Archive ouverte HAL Access content directly
Conference Papers Year :

Unsupervised Band Selection in Hyperspectral Images using Autoencoder


Hyperspectral images provide fine details of the observed scene from the exploitation of contiguous spectral bands. However, the high dimensionality of hyperspectral images causes a heavy burden on processing. Therefore, a common practice that has been largely adopted is the selection of bands before processing. Thus, in this work, a new unsupervised approach for band selection based on autoencoders is proposed. During the training phase of the autoencoder, the input data samples have some of their features turned to zero, through a masking noise transform. The subsequent reconstruction error is assigned to the indices with masking noise. The bigger the error, the greater the importance of the masked features. The errors are then summed up during the whole training phase. At the end, the bands corresponding to the biggest indices are selected. A comparison with four other band selection approaches reveals that the proposed method yields better results in some specific cases and similar results in other situations.
Fichier principal
Vignette du fichier
mateus_ICPRS2018_final (1).pdf (327.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01867374 , version 1 (14-11-2019)



Mateus Habermann, Vincent Frémont, Elcio H. Shiguemori. Unsupervised Band Selection in Hyperspectral Images using Autoencoder. 9th International Conference on Pattern Recognition Systems (ICPRS 2018), May 2018, Valparaiso, Chile. pp.28-33, ⟨10.1049/cp.2018.1282⟩. ⟨hal-01867374⟩
62 View
209 Download



Gmail Facebook Twitter LinkedIn More