Learning from label proportions for SAR image classification
Abstract Synthetic aperture radar (SAR) image classification plays a key role in SAR interpretation. Due to the cost and difficulty of truth labeling for SAR images, the newly labeled samples available for image classification are very limited. This paper focuses on defining a new sample labeling me...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-05-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13634-017-0478-8 |
| _version_ | 1818905506860761088 |
|---|---|
| author | Yongke Ding Yuanxiang Li Wenxian Yu |
| author_facet | Yongke Ding Yuanxiang Li Wenxian Yu |
| author_sort | Yongke Ding |
| collection | DOAJ |
| description | Abstract Synthetic aperture radar (SAR) image classification plays a key role in SAR interpretation. Due to the cost and difficulty of truth labeling for SAR images, the newly labeled samples available for image classification are very limited. This paper focuses on defining a new sample labeling method to solve the problem of truth acquisition for training data in SAR image classification. An efficient classification framework for high-resolution SAR images is presented in this paper, which is built on learning from uncertain labels. We use grid labeling for rapid training data acquisition by assigning a label to a group of neighboring pixels at a time. A novel SVM-based learning model is proposed to optimize the uncertain training data within the constraints of label proportions in each group and then predict the label of each sample for the test data based on the optimized training set. This work intends to explore a rapid labeling method called grid labeling for efficient training set definition and apply it to large-scale SAR image classification. The model demonstrates good performance in both accuracy and efficiency for scene interpretation of high-resolution SAR images. |
| first_indexed | 2024-12-19T21:24:25Z |
| format | Article |
| id | doaj.art-4687e1455072422c8d30cf344d27271e |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-12-19T21:24:25Z |
| publishDate | 2017-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-4687e1455072422c8d30cf344d27271e2022-12-21T20:05:10ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802017-05-012017111210.1186/s13634-017-0478-8Learning from label proportions for SAR image classificationYongke Ding0Yuanxiang Li1Wenxian Yu2Center for Advanced Sensing Technology, Shanghai Jiao Tong UniversitySchool of Aeronautics & Astronautics, Shanghai Jiao Tong UniversityCenter for Advanced Sensing Technology, Shanghai Jiao Tong UniversityAbstract Synthetic aperture radar (SAR) image classification plays a key role in SAR interpretation. Due to the cost and difficulty of truth labeling for SAR images, the newly labeled samples available for image classification are very limited. This paper focuses on defining a new sample labeling method to solve the problem of truth acquisition for training data in SAR image classification. An efficient classification framework for high-resolution SAR images is presented in this paper, which is built on learning from uncertain labels. We use grid labeling for rapid training data acquisition by assigning a label to a group of neighboring pixels at a time. A novel SVM-based learning model is proposed to optimize the uncertain training data within the constraints of label proportions in each group and then predict the label of each sample for the test data based on the optimized training set. This work intends to explore a rapid labeling method called grid labeling for efficient training set definition and apply it to large-scale SAR image classification. The model demonstrates good performance in both accuracy and efficiency for scene interpretation of high-resolution SAR images.http://link.springer.com/article/10.1186/s13634-017-0478-8SARImage classificationSVMLabel proportionLand cover |
| spellingShingle | Yongke Ding Yuanxiang Li Wenxian Yu Learning from label proportions for SAR image classification EURASIP Journal on Advances in Signal Processing SAR Image classification SVM Label proportion Land cover |
| title | Learning from label proportions for SAR image classification |
| title_full | Learning from label proportions for SAR image classification |
| title_fullStr | Learning from label proportions for SAR image classification |
| title_full_unstemmed | Learning from label proportions for SAR image classification |
| title_short | Learning from label proportions for SAR image classification |
| title_sort | learning from label proportions for sar image classification |
| topic | SAR Image classification SVM Label proportion Land cover |
| url | http://link.springer.com/article/10.1186/s13634-017-0478-8 |
| work_keys_str_mv | AT yongkeding learningfromlabelproportionsforsarimageclassification AT yuanxiangli learningfromlabelproportionsforsarimageclassification AT wenxianyu learningfromlabelproportionsforsarimageclassification |