Multi-scale guided feature extraction and classification algorithm for hyperspectral images

Abstract To solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image cla...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shiqi Huang, Ying Lu, Wenqing Wang, Ke Sun
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/79923162e6424f5583ae014451142508
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:79923162e6424f5583ae014451142508
record_format	dspace
spelling	oai:doaj.org-article:79923162e6424f5583ae0144511425082021-12-02T17:23:47ZMulti-scale guided feature extraction and classification algorithm for hyperspectral images10.1038/s41598-021-97636-22045-2322https://doaj.org/article/79923162e6424f5583ae0144511425082021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97636-2https://doaj.org/toc/2045-2322Abstract To solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image classification, and then proposes a multi-scale guided feature extraction and classification (MGFEC) algorithm for hyperspectral images. Firstly, the principal component analysis theory is used to reduce the dimension of hyperspectral image data. Then, guided filtering algorithm is used to achieve multi-scale spatial structure extraction of hyperspectral image by setting different sizes of filtering windows, so as to retain more edge details. Finally, the extracted multi-scale features are input into the support vector machine classifier for classification. Several practical hyperspectral image datasets were used to verify the experiment, and compared with other spectral feature extraction algorithms. The experimental results show that the multi-scale features extracted by the MGFEC algorithm proposed in this paper are more accurate than those extracted by only using spectral information, which leads to the improvement of the final classification accuracy. This fully shows that the proposed method is not only effective, but also suitable for processing different hyperspectral image data.Shiqi HuangYing LuWenqing WangKe SunNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Shiqi Huang Ying Lu Wenqing Wang Ke Sun Multi-scale guided feature extraction and classification algorithm for hyperspectral images
description	Abstract To solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image classification, and then proposes a multi-scale guided feature extraction and classification (MGFEC) algorithm for hyperspectral images. Firstly, the principal component analysis theory is used to reduce the dimension of hyperspectral image data. Then, guided filtering algorithm is used to achieve multi-scale spatial structure extraction of hyperspectral image by setting different sizes of filtering windows, so as to retain more edge details. Finally, the extracted multi-scale features are input into the support vector machine classifier for classification. Several practical hyperspectral image datasets were used to verify the experiment, and compared with other spectral feature extraction algorithms. The experimental results show that the multi-scale features extracted by the MGFEC algorithm proposed in this paper are more accurate than those extracted by only using spectral information, which leads to the improvement of the final classification accuracy. This fully shows that the proposed method is not only effective, but also suitable for processing different hyperspectral image data.
format	article
author	Shiqi Huang Ying Lu Wenqing Wang Ke Sun
author_facet	Shiqi Huang Ying Lu Wenqing Wang Ke Sun
author_sort	Shiqi Huang
title	Multi-scale guided feature extraction and classification algorithm for hyperspectral images
title_short	Multi-scale guided feature extraction and classification algorithm for hyperspectral images
title_full	Multi-scale guided feature extraction and classification algorithm for hyperspectral images
title_fullStr	Multi-scale guided feature extraction and classification algorithm for hyperspectral images
title_full_unstemmed	Multi-scale guided feature extraction and classification algorithm for hyperspectral images
title_sort	multi-scale guided feature extraction and classification algorithm for hyperspectral images
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/79923162e6424f5583ae014451142508
work_keys_str_mv	AT shiqihuang multiscaleguidedfeatureextractionandclassificationalgorithmforhyperspectralimages AT yinglu multiscaleguidedfeatureextractionandclassificationalgorithmforhyperspectralimages AT wenqingwang multiscaleguidedfeatureextractionandclassificationalgorithmforhyperspectralimages AT kesun multiscaleguidedfeatureextractionandclassificationalgorithmforhyperspectralimages
_version_	1718380978276139008

Multi-scale guided feature extraction and classification algorithm for hyperspectral images

Ejemplares similares