Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance
In the past few years, the sparse representation (SR) graph-based semi-supervised learning (SSL) has drawn a lot of attention for its impressive performance in hyperspectral image classification with small numbers of training samples. Among these methods, the probabilistic class structure regularize...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/21/7740 |
_version_ | 1797549090249113600 |
---|---|
author | Wanghao Xu Siqi Luo Yunfei Wang Youqiang Zhang Guo Cao |
author_facet | Wanghao Xu Siqi Luo Yunfei Wang Youqiang Zhang Guo Cao |
author_sort | Wanghao Xu |
collection | DOAJ |
description | In the past few years, the sparse representation (SR) graph-based semi-supervised learning (SSL) has drawn a lot of attention for its impressive performance in hyperspectral image classification with small numbers of training samples. Among these methods, the probabilistic class structure regularized sparse representation (PCSSR) approach, which introduces the probabilistic relationship between samples into the SR process, has shown its superiority over state-of-the-art approaches. However, this category of classification methods only apply another SR process to generate the probabilistic relationship, which focuses only on the spectral information but fails to utilize the spatial information. In this paper, we propose using the class adjusted spatial distance (CASD) to measure the distance between each two samples. We incorporate the proposed a CASD-based distance information into PCSSR mode to further increase the discriminability of original PCSSR approach. The proposed method considers not only the spectral information but also the spatial information of the hyperspectral data, consequently leading to significant performance improvement. Experimental results on different datasets demonstrate that compared with state-of-the-start classification models, the proposed method achieves the highest overall accuracies of 99.71%, 97.13%, and 97.07% on Botswana (BOT), Kennedy Space Center (KSC) and the truncated Indian Pines (PINE) datasets, respectively, with a small number of training samples selected from each class. |
first_indexed | 2024-03-10T15:09:41Z |
format | Article |
id | doaj.art-23e82c580b334511b7a2d8a97f0e4ed3 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T15:09:41Z |
publishDate | 2020-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-23e82c580b334511b7a2d8a97f0e4ed32023-11-20T19:27:13ZengMDPI AGApplied Sciences2076-34172020-11-011021774010.3390/app10217740Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial DistanceWanghao Xu0Siqi Luo1Yunfei Wang2Youqiang Zhang3Guo Cao4School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaIn the past few years, the sparse representation (SR) graph-based semi-supervised learning (SSL) has drawn a lot of attention for its impressive performance in hyperspectral image classification with small numbers of training samples. Among these methods, the probabilistic class structure regularized sparse representation (PCSSR) approach, which introduces the probabilistic relationship between samples into the SR process, has shown its superiority over state-of-the-art approaches. However, this category of classification methods only apply another SR process to generate the probabilistic relationship, which focuses only on the spectral information but fails to utilize the spatial information. In this paper, we propose using the class adjusted spatial distance (CASD) to measure the distance between each two samples. We incorporate the proposed a CASD-based distance information into PCSSR mode to further increase the discriminability of original PCSSR approach. The proposed method considers not only the spectral information but also the spatial information of the hyperspectral data, consequently leading to significant performance improvement. Experimental results on different datasets demonstrate that compared with state-of-the-start classification models, the proposed method achieves the highest overall accuracies of 99.71%, 97.13%, and 97.07% on Botswana (BOT), Kennedy Space Center (KSC) and the truncated Indian Pines (PINE) datasets, respectively, with a small number of training samples selected from each class.https://www.mdpi.com/2076-3417/10/21/7740hyperspectral image classificationsemi-supervised learningsparse representationspatial distance informationregularizer |
spellingShingle | Wanghao Xu Siqi Luo Yunfei Wang Youqiang Zhang Guo Cao Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance Applied Sciences hyperspectral image classification semi-supervised learning sparse representation spatial distance information regularizer |
title | Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance |
title_full | Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance |
title_fullStr | Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance |
title_full_unstemmed | Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance |
title_short | Sparse Representation Graph for Hyperspectral Image Classification Assisted by Class Adjusted Spatial Distance |
title_sort | sparse representation graph for hyperspectral image classification assisted by class adjusted spatial distance |
topic | hyperspectral image classification semi-supervised learning sparse representation spatial distance information regularizer |
url | https://www.mdpi.com/2076-3417/10/21/7740 |
work_keys_str_mv | AT wanghaoxu sparserepresentationgraphforhyperspectralimageclassificationassistedbyclassadjustedspatialdistance AT siqiluo sparserepresentationgraphforhyperspectralimageclassificationassistedbyclassadjustedspatialdistance AT yunfeiwang sparserepresentationgraphforhyperspectralimageclassificationassistedbyclassadjustedspatialdistance AT youqiangzhang sparserepresentationgraphforhyperspectralimageclassificationassistedbyclassadjustedspatialdistance AT guocao sparserepresentationgraphforhyperspectralimageclassificationassistedbyclassadjustedspatialdistance |