Unsupervised Spectral-Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery Classification

In this letter, different from traditional methods using original spectral features or handcraft spectral-spatial features, we propose to adaptively learn a suitable feature representation from unlabeled data. This is achieved by learning a feature mapping function based on stacked sparse autoencode...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE geoscience and remote sensing letters Jg. 12; H. 12; S. 2438 - 2442
Hauptverfasser:	Tao, Chao, Pan, Hongbo, Li, Yansheng, Zou, Zhengrou
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.12.2015 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Classification Feature extraction Hyperspectral imagery (HSI) classification Hyperspectral imaging Image acquisition Image classification Learning linear support vector machine Remote sensing Representations Spectra spectral-spatial feature learning stacked sparse autoencoder (SSAE) Support vector machines Training Training data spectral–spatial feature learning stacked sparse autoencoder (SSAE) linear support vector machine Hyperspectral imagery (HSI) classification
ISSN:	1545-598X, 1558-0571
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!