Hyperspectral image classification using k-sparse denoising autoencoder and spectral–restricted spatial characteristics

Hyperspectral images (HSIs) have both spectral and spatial characteristics that possess considerable information. This paper proposes a novel k-sparse denoising autoencoder (KDAE) with a softmax classifier for HSI classification. Based on the stack-type autoencoder, KDAE adopts k-sparsity and random...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied soft computing Jg. 74; S. 693 - 708
Hauptverfasser: Lan, Rushi, Li, Zeya, Liu, Zhenbing, Gu, Tianlong, Luo, Xiaonan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.01.2019
Schlagworte:
Hyperspectral image classification
k-sparse denoising autoencoders
Restricted spatial information
Softmax
Softmax
Restricted spatial information
k-sparse denoising autoencoders
Hyperspectral image classification
ISSN:1568-4946, 1872-9681
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Hyperspectral images (HSIs) have both spectral and spatial characteristics that possess considerable information. This paper proposes a novel k-sparse denoising autoencoder (KDAE) with a softmax classifier for HSI classification. Based on the stack-type autoencoder, KDAE adopts k-sparsity and random noise, employs the dropout method at the hidden layers, and finally classifies HSIs through the softmax classifier. Moreover, an operation referred to as restricted spatial information (RSI) is conducted to obtain the spatial information of the HSI. The proposed method extracts features by KDAE combined with RSI, effectively taking the spectral and spatial information into account. The obtained features are finally fed into the softmax classifier for classification. The experimental results obtained on two benchmark hyperspectral datasets indicate that the proposed method achieves state-of-the-art performance compared with other competing methods. •Propose k-sparse denoising autoencoders (KDAE) to extract the features of hyperspectral images.•Develop spectral–restricted spatial characteristics for hyperspectral images.•A framework, integrating k-sparse denoising autoencoders and spectral–restricted spatial characteristics, is proposed for hyperspectral image classification.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2018.08.049