Cargando…
Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification
A hyperspectral image (HSI), which contains a number of contiguous and narrow spectral wavelength bands, is a valuable source of data for ground cover examinations. Classification using the entire original HSI suffers from the “curse of dimensionality” problem because (i) the image bands are highly...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9864404/ https://www.ncbi.nlm.nih.gov/pubmed/36679453 http://dx.doi.org/10.3390/s23020657 |
_version_ | 1784875576190828544 |
---|---|
author | Islam, Md Rashedul Ahmed, Boshir Hossain, Md Ali Uddin, Md Palash |
author_facet | Islam, Md Rashedul Ahmed, Boshir Hossain, Md Ali Uddin, Md Palash |
author_sort | Islam, Md Rashedul |
collection | PubMed |
description | A hyperspectral image (HSI), which contains a number of contiguous and narrow spectral wavelength bands, is a valuable source of data for ground cover examinations. Classification using the entire original HSI suffers from the “curse of dimensionality” problem because (i) the image bands are highly correlated both spectrally and spatially, (ii) not every band can carry equal information, (iii) there is a lack of enough training samples for some classes, and (iv) the overall computational cost is high. Therefore, effective feature (band) reduction is necessary through feature extraction (FE) and/or feature selection (FS) for improving the classification in a cost-effective manner. Principal component analysis (PCA) is a frequently adopted unsupervised FE method in HSI classification. Nevertheless, its performance worsens when the dataset is noisy, and the computational cost becomes high. Consequently, this study first proposed an efficient FE approach using a normalized mutual information (NMI)-based band grouping strategy, where the classical PCA was applied to each band subgroup for intrinsic FE. Finally, the subspace of the most effective features was generated by the NMI-based minimum redundancy and maximum relevance (mRMR) FS criteria. The subspace of features was then classified using the kernel support vector machine. Two real HSIs collected by the AVIRIS and HYDICE sensors were used in an experiment. The experimental results demonstrated that the proposed feature reduction approach significantly improved the classification performance. It achieved the highest overall classification accuracy of 94.93% for the AVIRIS dataset and 99.026% for the HYDICE dataset. Moreover, the proposed approach reduced the computational cost compared with the studied methods. |
format | Online Article Text |
id | pubmed-9864404 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-98644042023-01-22 Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification Islam, Md Rashedul Ahmed, Boshir Hossain, Md Ali Uddin, Md Palash Sensors (Basel) Article A hyperspectral image (HSI), which contains a number of contiguous and narrow spectral wavelength bands, is a valuable source of data for ground cover examinations. Classification using the entire original HSI suffers from the “curse of dimensionality” problem because (i) the image bands are highly correlated both spectrally and spatially, (ii) not every band can carry equal information, (iii) there is a lack of enough training samples for some classes, and (iv) the overall computational cost is high. Therefore, effective feature (band) reduction is necessary through feature extraction (FE) and/or feature selection (FS) for improving the classification in a cost-effective manner. Principal component analysis (PCA) is a frequently adopted unsupervised FE method in HSI classification. Nevertheless, its performance worsens when the dataset is noisy, and the computational cost becomes high. Consequently, this study first proposed an efficient FE approach using a normalized mutual information (NMI)-based band grouping strategy, where the classical PCA was applied to each band subgroup for intrinsic FE. Finally, the subspace of the most effective features was generated by the NMI-based minimum redundancy and maximum relevance (mRMR) FS criteria. The subspace of features was then classified using the kernel support vector machine. Two real HSIs collected by the AVIRIS and HYDICE sensors were used in an experiment. The experimental results demonstrated that the proposed feature reduction approach significantly improved the classification performance. It achieved the highest overall classification accuracy of 94.93% for the AVIRIS dataset and 99.026% for the HYDICE dataset. Moreover, the proposed approach reduced the computational cost compared with the studied methods. MDPI 2023-01-06 /pmc/articles/PMC9864404/ /pubmed/36679453 http://dx.doi.org/10.3390/s23020657 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Islam, Md Rashedul Ahmed, Boshir Hossain, Md Ali Uddin, Md Palash Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification |
title | Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification |
title_full | Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification |
title_fullStr | Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification |
title_full_unstemmed | Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification |
title_short | Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification |
title_sort | mutual information-driven feature reduction for hyperspectral image classification |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9864404/ https://www.ncbi.nlm.nih.gov/pubmed/36679453 http://dx.doi.org/10.3390/s23020657 |
work_keys_str_mv | AT islammdrashedul mutualinformationdrivenfeaturereductionforhyperspectralimageclassification AT ahmedboshir mutualinformationdrivenfeaturereductionforhyperspectralimageclassification AT hossainmdali mutualinformationdrivenfeaturereductionforhyperspectralimageclassification AT uddinmdpalash mutualinformationdrivenfeaturereductionforhyperspectralimageclassification |