Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother
ABSTRACTIn this paper, a multi-strategy fusion (MSF) framework, based on improved MBLBP and bi-exponential edge-preserving smoother (BEEPS), is proposed for hyperspectral image (HSI) classification. First, MBLBP operator is adopted to characterize the overall structural information of HSI, where the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/22797254.2023.2237654 |
| _version_ | 1797771250318180352 |
|---|---|
| author | Xiaoqing Wan Shuanghao Chen |
| author_facet | Xiaoqing Wan Shuanghao Chen |
| author_sort | Xiaoqing Wan |
| collection | DOAJ |
| description | ABSTRACTIn this paper, a multi-strategy fusion (MSF) framework, based on improved MBLBP and bi-exponential edge-preserving smoother (BEEPS), is proposed for hyperspectral image (HSI) classification. First, MBLBP operator is adopted to characterize the overall structural information of HSI, where the averaging strategy allocates same weights for the pixels in a local sub-region, so that the edges tend to be blurred due to being isotropic. To solve this question, the steering kernel is first introduced into MBLBP for learning the local structure prior of HSI. Then, a support vector machine classifier is used to calculate the soft classified probabilities of pixels. Furthermore, BEEPS is adopted to smooth the soft classified probabilities maps in the post-processing stage, and the purpose is to further improve classification accuracy of HSI by considering context-aware information for each class label. Experiments are performed on three real hyperspectral datasets, namely, Indian Pines, KSC, and Houston 2013, only 1%, 6, and 5 labeled samples are randomly selected for training, the overall accuracy(kappa) obtained by MSF is 99.47%(99.40), 99.52%(99.47), and 94.25%(93.78), respectively, which is far better than the contrast methods. |
| first_indexed | 2024-03-12T21:33:51Z |
| format | Article |
| id | doaj.art-b7ee3b37c4d9408782ea57ee35d8b11c |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-03-12T21:33:51Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-b7ee3b37c4d9408782ea57ee35d8b11c2023-07-27T13:42:36ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542023-12-0156110.1080/22797254.2023.2237654Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smootherXiaoqing Wan0Shuanghao Chen1College of Computer Science and Technology, Hengyang Normal University, Hengyang, ChinaCollege of Computer and Engineering, Zhengzhou University, Zhengzhou, ChinaABSTRACTIn this paper, a multi-strategy fusion (MSF) framework, based on improved MBLBP and bi-exponential edge-preserving smoother (BEEPS), is proposed for hyperspectral image (HSI) classification. First, MBLBP operator is adopted to characterize the overall structural information of HSI, where the averaging strategy allocates same weights for the pixels in a local sub-region, so that the edges tend to be blurred due to being isotropic. To solve this question, the steering kernel is first introduced into MBLBP for learning the local structure prior of HSI. Then, a support vector machine classifier is used to calculate the soft classified probabilities of pixels. Furthermore, BEEPS is adopted to smooth the soft classified probabilities maps in the post-processing stage, and the purpose is to further improve classification accuracy of HSI by considering context-aware information for each class label. Experiments are performed on three real hyperspectral datasets, namely, Indian Pines, KSC, and Houston 2013, only 1%, 6, and 5 labeled samples are randomly selected for training, the overall accuracy(kappa) obtained by MSF is 99.47%(99.40), 99.52%(99.47), and 94.25%(93.78), respectively, which is far better than the contrast methods.https://www.tandfonline.com/doi/10.1080/22797254.2023.2237654Classificationhyperspectral imagemultiple strategy fusionmulti-scale block local binary patternedge-preserving filtering |
| spellingShingle | Xiaoqing Wan Shuanghao Chen Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother European Journal of Remote Sensing Classification hyperspectral image multiple strategy fusion multi-scale block local binary pattern edge-preserving filtering |
| title | Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother |
| title_full | Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother |
| title_fullStr | Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother |
| title_full_unstemmed | Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother |
| title_short | Hyperspectral image classification using improved multi-scale block local binary pattern and bi-exponential edge-preserving smoother |
| title_sort | hyperspectral image classification using improved multi scale block local binary pattern and bi exponential edge preserving smoother |
| topic | Classification hyperspectral image multiple strategy fusion multi-scale block local binary pattern edge-preserving filtering |
| url | https://www.tandfonline.com/doi/10.1080/22797254.2023.2237654 |
| work_keys_str_mv | AT xiaoqingwan hyperspectralimageclassificationusingimprovedmultiscaleblocklocalbinarypatternandbiexponentialedgepreservingsmoother AT shuanghaochen hyperspectralimageclassificationusingimprovedmultiscaleblocklocalbinarypatternandbiexponentialedgepreservingsmoother |