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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters Vol. 12; no. 12; pp. 2438 - 2442
Main Authors: Tao, Chao, Pan, Hongbo, Li, Yansheng, Zou, Zhengrou
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.12.2015
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
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 Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 autoencoder. Considering that hyperspectral imagery (HSI) is intrinsically defined in both the spectral and spatial domains, we further establish two variants of feature learning procedures for sparse spectral feature learning and multiscale spatial feature learning. Finally, we embed the learned spectral-spatial feature into a linear support vector machine for classification. Experiments on two hyperspectral images indicate the following: 1) the learned spectral-spatial feature representation is more discriminative for HSI classification compared to previously hand-engineered spectral-spatial features, especially when the training data are limited and 2) the learned features appear not to be specific to a particular image but general in that they are applicable to multiple related images (e.g., images acquired by the same sensor but varying with location or time).
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2015.2482520