A Collaborative Despeckling Method for SAR Images Based on Texture Classification
Speckle is an unavoidable noise-like phenomenon in Synthetic Aperture Radar (SAR) imaging. In order to remove speckle, many despeckling methods have been proposed during the past three decades, including spatial-based methods, transform domain-based methods, and non-local filtering methods. However,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/6/1465 |
| _version_ | 1797442632434057216 |
|---|---|
| author | Gongtang Wang Fuyu Bo Xue Chen Wenfeng Lu Shaohai Hu Jing Fang |
| author_facet | Gongtang Wang Fuyu Bo Xue Chen Wenfeng Lu Shaohai Hu Jing Fang |
| author_sort | Gongtang Wang |
| collection | DOAJ |
| description | Speckle is an unavoidable noise-like phenomenon in Synthetic Aperture Radar (SAR) imaging. In order to remove speckle, many despeckling methods have been proposed during the past three decades, including spatial-based methods, transform domain-based methods, and non-local filtering methods. However, SAR images usually contain many different types of regions, including homogeneous and heterogeneous regions. Some filters could despeckle effectively in homogeneous regions but could not preserve structures in heterogeneous regions. Some filters preserve structures well but do not suppress speckle effectively. Following this theory, we design a combination of two state-of-the-art despeckling tools that can overcome their respective shortcomings. In order to select the best filter output for each area in the image, the clustering and Gray Level Co-Occurrence Matrices (GLCM) are used for image classification and weighting, respectively. Clustering and GLCM use the co-registered optical images of SAR images because their structure information is consistent, and the optical images are much cleaner than SAR images. The experimental results on synthetic and real-world SAR images show that our proposed method can provide a better objective performance index under a strong noise level. Subjective visual inspection demonstrates that the proposed method has great potential in preserving structural details and suppressing speckle noise. |
| first_indexed | 2024-03-09T12:44:45Z |
| format | Article |
| id | doaj.art-4f5e4e01b09d407291481dce7add3105 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:44:45Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4f5e4e01b09d407291481dce7add31052023-11-30T22:13:24ZengMDPI AGRemote Sensing2072-42922022-03-01146146510.3390/rs14061465A Collaborative Despeckling Method for SAR Images Based on Texture ClassificationGongtang Wang0Fuyu Bo1Xue Chen2Wenfeng Lu3Shaohai Hu4Jing Fang5School of Physics and Electronics, Shandong Normal University, Jinan 250014, ChinaSchool of Physics and Electronics, Shandong Normal University, Jinan 250014, ChinaSchool of Physics and Electronics, Shandong Normal University, Jinan 250014, ChinaSchool of Management Engineering, Shandong Jianzhu University, Jinan 250101, ChinaInstitute of Information Science, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Physics and Electronics, Shandong Normal University, Jinan 250014, ChinaSpeckle is an unavoidable noise-like phenomenon in Synthetic Aperture Radar (SAR) imaging. In order to remove speckle, many despeckling methods have been proposed during the past three decades, including spatial-based methods, transform domain-based methods, and non-local filtering methods. However, SAR images usually contain many different types of regions, including homogeneous and heterogeneous regions. Some filters could despeckle effectively in homogeneous regions but could not preserve structures in heterogeneous regions. Some filters preserve structures well but do not suppress speckle effectively. Following this theory, we design a combination of two state-of-the-art despeckling tools that can overcome their respective shortcomings. In order to select the best filter output for each area in the image, the clustering and Gray Level Co-Occurrence Matrices (GLCM) are used for image classification and weighting, respectively. Clustering and GLCM use the co-registered optical images of SAR images because their structure information is consistent, and the optical images are much cleaner than SAR images. The experimental results on synthetic and real-world SAR images show that our proposed method can provide a better objective performance index under a strong noise level. Subjective visual inspection demonstrates that the proposed method has great potential in preserving structural details and suppressing speckle noise.https://www.mdpi.com/2072-4292/14/6/1465Synthetic Aperture Radar (SAR)despecklingclusteringGray Level Co-Occurrence Matrices (GLCM) |
| spellingShingle | Gongtang Wang Fuyu Bo Xue Chen Wenfeng Lu Shaohai Hu Jing Fang A Collaborative Despeckling Method for SAR Images Based on Texture Classification Remote Sensing Synthetic Aperture Radar (SAR) despeckling clustering Gray Level Co-Occurrence Matrices (GLCM) |
| title | A Collaborative Despeckling Method for SAR Images Based on Texture Classification |
| title_full | A Collaborative Despeckling Method for SAR Images Based on Texture Classification |
| title_fullStr | A Collaborative Despeckling Method for SAR Images Based on Texture Classification |
| title_full_unstemmed | A Collaborative Despeckling Method for SAR Images Based on Texture Classification |
| title_short | A Collaborative Despeckling Method for SAR Images Based on Texture Classification |
| title_sort | collaborative despeckling method for sar images based on texture classification |
| topic | Synthetic Aperture Radar (SAR) despeckling clustering Gray Level Co-Occurrence Matrices (GLCM) |
| url | https://www.mdpi.com/2072-4292/14/6/1465 |
| work_keys_str_mv | AT gongtangwang acollaborativedespecklingmethodforsarimagesbasedontextureclassification AT fuyubo acollaborativedespecklingmethodforsarimagesbasedontextureclassification AT xuechen acollaborativedespecklingmethodforsarimagesbasedontextureclassification AT wenfenglu acollaborativedespecklingmethodforsarimagesbasedontextureclassification AT shaohaihu acollaborativedespecklingmethodforsarimagesbasedontextureclassification AT jingfang acollaborativedespecklingmethodforsarimagesbasedontextureclassification AT gongtangwang collaborativedespecklingmethodforsarimagesbasedontextureclassification AT fuyubo collaborativedespecklingmethodforsarimagesbasedontextureclassification AT xuechen collaborativedespecklingmethodforsarimagesbasedontextureclassification AT wenfenglu collaborativedespecklingmethodforsarimagesbasedontextureclassification AT shaohaihu collaborativedespecklingmethodforsarimagesbasedontextureclassification AT jingfang collaborativedespecklingmethodforsarimagesbasedontextureclassification |