Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification
The superpixel-based multiple kernels model uses the average value of all pixels within superpixel as the spatial feature, which results in inaccurate extraction of edge pixels. To solve this problem, a local binary patterns and superpixel-based multiple kernels method is proposed for hyperspectral...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9160871/ |
id |
doaj-ddde7350ca3244f0a33db6e1b33e7892 |
---|---|
record_format |
Article |
spelling |
doaj-ddde7350ca3244f0a33db6e1b33e78922021-06-03T23:07:13ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01134550456310.1109/JSTARS.2020.30144929160871Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image ClassificationWei Huang0https://orcid.org/0000-0002-5499-3728Yao Huang1Hua Wang2Yan Liu3Hiuk Jae Shim4School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, ChinaCollege of Electronic and Electrical Engineering, Sungkyunkwan University, Suwon, South KoreaThe superpixel-based multiple kernels model uses the average value of all pixels within superpixel as the spatial feature, which results in inaccurate extraction of edge pixels. To solve this problem, a local binary patterns and superpixel-based multiple kernels method is proposed for hyperspectral image (HSI) classification. First, the original HSI is segmented into multiple superpixels by using the entropy rate superpixel segmentation algorithm. On the HSI with superpixel index, the spectral kernel is second obtained by combining the spectral feature map with the radial basis kernel (RBF). By introducing local binary pattern (LBP) and weighted average filtering into RBF, the spatial kernels are obtained within and among superpixels. Finally, the combined kernel containing the abovementioned three kernels is inputted into the support vector machine classifier to generate a classification map. The experimental procedure in this article uses LBP to extract the information in superpixels, which effectively prevents the loss of edge features in superpixels. The experimental results show that the proposed method is superior to the state-of-the-art classifiers for HSI classification.https://ieeexplore.ieee.org/document/9160871/Hyperspectral image (HSI)local binary mode (LBP)multiple kernels (MK)superpixelsupport vector machine (SVM) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wei Huang Yao Huang Hua Wang Yan Liu Hiuk Jae Shim |
spellingShingle |
Wei Huang Yao Huang Hua Wang Yan Liu Hiuk Jae Shim Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Hyperspectral image (HSI) local binary mode (LBP) multiple kernels (MK) superpixel support vector machine (SVM) |
author_facet |
Wei Huang Yao Huang Hua Wang Yan Liu Hiuk Jae Shim |
author_sort |
Wei Huang |
title |
Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification |
title_short |
Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification |
title_full |
Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification |
title_fullStr |
Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification |
title_full_unstemmed |
Local Binary Patterns and Superpixel-Based Multiple Kernels for Hyperspectral Image Classification |
title_sort |
local binary patterns and superpixel-based multiple kernels for hyperspectral image classification |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2020-01-01 |
description |
The superpixel-based multiple kernels model uses the average value of all pixels within superpixel as the spatial feature, which results in inaccurate extraction of edge pixels. To solve this problem, a local binary patterns and superpixel-based multiple kernels method is proposed for hyperspectral image (HSI) classification. First, the original HSI is segmented into multiple superpixels by using the entropy rate superpixel segmentation algorithm. On the HSI with superpixel index, the spectral kernel is second obtained by combining the spectral feature map with the radial basis kernel (RBF). By introducing local binary pattern (LBP) and weighted average filtering into RBF, the spatial kernels are obtained within and among superpixels. Finally, the combined kernel containing the abovementioned three kernels is inputted into the support vector machine classifier to generate a classification map. The experimental procedure in this article uses LBP to extract the information in superpixels, which effectively prevents the loss of edge features in superpixels. The experimental results show that the proposed method is superior to the state-of-the-art classifiers for HSI classification. |
topic |
Hyperspectral image (HSI) local binary mode (LBP) multiple kernels (MK) superpixel support vector machine (SVM) |
url |
https://ieeexplore.ieee.org/document/9160871/ |
work_keys_str_mv |
AT weihuang localbinarypatternsandsuperpixelbasedmultiplekernelsforhyperspectralimageclassification AT yaohuang localbinarypatternsandsuperpixelbasedmultiplekernelsforhyperspectralimageclassification AT huawang localbinarypatternsandsuperpixelbasedmultiplekernelsforhyperspectralimageclassification AT yanliu localbinarypatternsandsuperpixelbasedmultiplekernelsforhyperspectralimageclassification AT hiukjaeshim localbinarypatternsandsuperpixelbasedmultiplekernelsforhyperspectralimageclassification |
_version_ |
1721398619632828416 |