Hyperspectral image classification using an extended Auto-Encoder method

Kordi Ghasrodashti, E; Sharma, N

Hyperspectral image classification using an extended Auto-Encoder method

Kordi Ghasrodashti, E Sharma, N

Permalink

Publisher:: Elsevier BV
Publication Type:: Journal Article
Citation:: Signal Processing: Image Communication, 2021, 92, pp. 116111
Issue Date:: 2021-03-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0923596520302290-main.pdf	Published version	2.96 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Kordi Ghasrodashti, E
dc.contributor.author	Sharma, N https://orcid.org/0000-0003-0841-1245
dc.date.accessioned	2022-05-03T20:16:55Z
dc.date.available	2022-05-03T20:16:55Z
dc.date.issued	2021-03-01
dc.identifier.citation	Signal Processing: Image Communication, 2021, 92, pp. 116111
dc.identifier.issn	0923-5965
dc.identifier.uri	http://hdl.handle.net/10453/156972
dc.description.abstract	This article proposes a spectral–spatial method for classification of hyperspectral images (HSIs) by modifying traditional Auto-Encoder based on Majorization Minimization (MM) technique. The proposed method consists of suggesting three main modifications. First, to construct weights of Auto-Encoder, similarity angle map(SAM) criterion is used as regularization term. It is useful to extract spectral similarity of initial features. Second, to enhance the classification accuracy, fuzzy mode is used to estimate parameters. These modifications lead to create an extended Auto-Encoder based on MM (EAEMM). Third, to improve the performance of Auto-Encoder, multi-scale features (MSF) are extracted. In comparison with some of the state-of-the-art methods, the experimental results obtained using the proposed method (MSF-EAEMM) show that it significantly improves the classification accuracy of HSI classification.
dc.language	en
dc.publisher	Elsevier BV
dc.relation.ispartof	Signal Processing: Image Communication
dc.relation.isbasedon	10.1016/j.image.2020.116111
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Hyperspectral image classification using an extended Auto-Encoder method
dc.type	Journal Article
utslib.citation.volume	92
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2022-05-03T20:16:53Z
pubs.publication-status	Published
pubs.volume	92

Abstract:

This article proposes a spectral–spatial method for classification of hyperspectral images (HSIs) by modifying traditional Auto-Encoder based on Majorization Minimization (MM) technique. The proposed method consists of suggesting three main modifications. First, to construct weights of Auto-Encoder, similarity angle map(SAM) criterion is used as regularization term. It is useful to extract spectral similarity of initial features. Second, to enhance the classification accuracy, fuzzy mode is used to estimate parameters. These modifications lead to create an extended Auto-Encoder based on MM (EAEMM). Third, to improve the performance of Auto-Encoder, multi-scale features (MSF) are extracted. In comparison with some of the state-of-the-art methods, the experimental results obtained using the proposed method (MSF-EAEMM) show that it significantly improves the classification accuracy of HSI classification.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/156972