Image classification of hyperspectral remote sensing using semi-supervised learning algorithm
Hyperspectral images contain abundant spectral and spatial information of the surface of the earth, but there are more difficulties in processing, analyzing, and sample-labeling these hyperspectral images. In this paper, local binary pattern (LBP), sparse representation and mixed logistic regression...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-05-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023510?viewType=HTML |
| _version_ | 1797822211345612800 |
|---|---|
| author | Ansheng Ye Xiangbing Zhou Kai Weng Yu Gong Fang Miao Huimin Zhao |
| author_facet | Ansheng Ye Xiangbing Zhou Kai Weng Yu Gong Fang Miao Huimin Zhao |
| author_sort | Ansheng Ye |
| collection | DOAJ |
| description | Hyperspectral images contain abundant spectral and spatial information of the surface of the earth, but there are more difficulties in processing, analyzing, and sample-labeling these hyperspectral images. In this paper, local binary pattern (LBP), sparse representation and mixed logistic regression model are introduced to propose a sample labeling method based on neighborhood information and priority classifier discrimination. A new hyperspectral remote sensing image classification method based on texture features and semi-supervised learning is implemented. The LBP is employed to extract features of spatial texture information from remote sensing images and enrich the feature information of samples. The multivariate logistic regression model is used to select the unlabeled samples with the largest amount of information, and the unlabeled samples with neighborhood information and priority classifier discrimination are selected to obtain the pseudo-labeled samples after learning. By making full use of the advantages of sparse representation and mixed logistic regression model, a new classification method based on semi-supervised learning is proposed to effectively achieve accurate classification of hyperspectral images. The data of Indian Pines, Salinas scene and Pavia University are selected to verify the validity of the proposed method. The experiment results have demonstrated that the proposed classification method is able to gain a higher classification accuracy, a stronger timeliness, and the generalization ability. |
| first_indexed | 2024-03-13T10:04:36Z |
| format | Article |
| id | doaj.art-a9a0f1c1ba644a88adbe0acd590f758e |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-03-13T10:04:36Z |
| publishDate | 2023-05-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-a9a0f1c1ba644a88adbe0acd590f758e2023-05-23T01:41:30ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-05-01206115021152710.3934/mbe.2023510Image classification of hyperspectral remote sensing using semi-supervised learning algorithmAnsheng Ye 0Xiangbing Zhou1Kai Weng2Yu Gong3Fang Miao 4Huimin Zhao51. Key Lab of Earth Exploration & Information Techniques of Ministry Education, Chengdu University of Technology, Chengdu 610059, China 2. School of Computer Science, Chengdu University, Chengdu 610106, China3. School of Information and Engineering, Sichuan Tourism University, Chengdu 610100, China4. Publicity and Information Center, Sichuan Provincial Department of Culture and Tourism, Chengdu 611930, China5. College of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, China1. Key Lab of Earth Exploration & Information Techniques of Ministry Education, Chengdu University of Technology, Chengdu 610059, China5. College of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaHyperspectral images contain abundant spectral and spatial information of the surface of the earth, but there are more difficulties in processing, analyzing, and sample-labeling these hyperspectral images. In this paper, local binary pattern (LBP), sparse representation and mixed logistic regression model are introduced to propose a sample labeling method based on neighborhood information and priority classifier discrimination. A new hyperspectral remote sensing image classification method based on texture features and semi-supervised learning is implemented. The LBP is employed to extract features of spatial texture information from remote sensing images and enrich the feature information of samples. The multivariate logistic regression model is used to select the unlabeled samples with the largest amount of information, and the unlabeled samples with neighborhood information and priority classifier discrimination are selected to obtain the pseudo-labeled samples after learning. By making full use of the advantages of sparse representation and mixed logistic regression model, a new classification method based on semi-supervised learning is proposed to effectively achieve accurate classification of hyperspectral images. The data of Indian Pines, Salinas scene and Pavia University are selected to verify the validity of the proposed method. The experiment results have demonstrated that the proposed classification method is able to gain a higher classification accuracy, a stronger timeliness, and the generalization ability.https://www.aimspress.com/article/doi/10.3934/mbe.2023510?viewType=HTMLhyperspectral remote sensing imagelocal binary patternsparse representationmixed logistic regressionneighborhood information |
| spellingShingle | Ansheng Ye Xiangbing Zhou Kai Weng Yu Gong Fang Miao Huimin Zhao Image classification of hyperspectral remote sensing using semi-supervised learning algorithm Mathematical Biosciences and Engineering hyperspectral remote sensing image local binary pattern sparse representation mixed logistic regression neighborhood information |
| title | Image classification of hyperspectral remote sensing using semi-supervised learning algorithm |
| title_full | Image classification of hyperspectral remote sensing using semi-supervised learning algorithm |
| title_fullStr | Image classification of hyperspectral remote sensing using semi-supervised learning algorithm |
| title_full_unstemmed | Image classification of hyperspectral remote sensing using semi-supervised learning algorithm |
| title_short | Image classification of hyperspectral remote sensing using semi-supervised learning algorithm |
| title_sort | image classification of hyperspectral remote sensing using semi supervised learning algorithm |
| topic | hyperspectral remote sensing image local binary pattern sparse representation mixed logistic regression neighborhood information |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023510?viewType=HTML |
| work_keys_str_mv | AT anshengye imageclassificationofhyperspectralremotesensingusingsemisupervisedlearningalgorithm AT xiangbingzhou imageclassificationofhyperspectralremotesensingusingsemisupervisedlearningalgorithm AT kaiweng imageclassificationofhyperspectralremotesensingusingsemisupervisedlearningalgorithm AT yugong imageclassificationofhyperspectralremotesensingusingsemisupervisedlearningalgorithm AT fangmiao imageclassificationofhyperspectralremotesensingusingsemisupervisedlearningalgorithm AT huiminzhao imageclassificationofhyperspectralremotesensingusingsemisupervisedlearningalgorithm |