Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System
The seed oil of Xanthoceras sorbifolium is a new kind of vegetable oil which is beneficial to the body. However, during the ripening process, if not picked properly, resulting in seed waste and economic loss. Therefore, selecting the right picking time is of great significance for improving seed yie...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10374360/ |
| _version_ | 1797361473046970368 |
|---|---|
| author | Zhang Dan Liu Zuchen Cheng Liying Li Tieshan Gu Liru |
| author_facet | Zhang Dan Liu Zuchen Cheng Liying Li Tieshan Gu Liru |
| author_sort | Zhang Dan |
| collection | DOAJ |
| description | The seed oil of Xanthoceras sorbifolium is a new kind of vegetable oil which is beneficial to the body. However, during the ripening process, if not picked properly, resulting in seed waste and economic loss. Therefore, selecting the right picking time is of great significance for improving seed yield, reducing waste of labor and capital costs, and improving economic benefits. It is very challenging to achieve real-time and accurate classification of the images in the ripening stage of Xanthoceras sorbifolium with similar color, different shapes and serious background interference. So as to extract effective fruit features and improve the classification efficiency, a broad learning image classification method based on feature excitation (BL-SENet) was proposed in this paper. Firstly, a broad learning system (BLS) was constructed to extract the fruit features based on node activation function for the input layer. Secondly, feature excitation is carried out based on SENet, and the learning weights of features extracted based on broad learning mechanism are re-calibrated to improve the accuracy of network classification. Finally, based on the feature calibration, image classification is carried out by taking full advantage of the fast broad learning system. It is tested through experiments, the training accuracy of the proposed method is 100%, and the test accuracy is more than 80%, and it is the fastest among the comparison methods (except BLS). In order to promote the development of intelligent agriculture and realize intelligent mechanical picking, it provides effective visual information. |
| first_indexed | 2024-03-08T15:55:10Z |
| format | Article |
| id | doaj.art-fd76f7d632434a4ea9ff077b0074fcf4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T15:55:10Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fd76f7d632434a4ea9ff077b0074fcf42024-01-09T00:04:27ZengIEEEIEEE Access2169-35362024-01-01123012302310.1109/ACCESS.2023.334761410374360Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning SystemZhang Dan0https://orcid.org/0000-0002-5788-8851Liu Zuchen1Cheng Liying2https://orcid.org/0009-0002-3071-4920Li Tieshan3https://orcid.org/0000-0003-0474-953XGu Liru4College of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian, ChinaSchool of Physical Science and Technology, Shenyang Normal University, Shenyang, ChinaSchool of Physical Science and Technology, Shenyang Normal University, Shenyang, ChinaSchool of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Physical Science and Technology, Shenyang Normal University, Shenyang, ChinaThe seed oil of Xanthoceras sorbifolium is a new kind of vegetable oil which is beneficial to the body. However, during the ripening process, if not picked properly, resulting in seed waste and economic loss. Therefore, selecting the right picking time is of great significance for improving seed yield, reducing waste of labor and capital costs, and improving economic benefits. It is very challenging to achieve real-time and accurate classification of the images in the ripening stage of Xanthoceras sorbifolium with similar color, different shapes and serious background interference. So as to extract effective fruit features and improve the classification efficiency, a broad learning image classification method based on feature excitation (BL-SENet) was proposed in this paper. Firstly, a broad learning system (BLS) was constructed to extract the fruit features based on node activation function for the input layer. Secondly, feature excitation is carried out based on SENet, and the learning weights of features extracted based on broad learning mechanism are re-calibrated to improve the accuracy of network classification. Finally, based on the feature calibration, image classification is carried out by taking full advantage of the fast broad learning system. It is tested through experiments, the training accuracy of the proposed method is 100%, and the test accuracy is more than 80%, and it is the fastest among the comparison methods (except BLS). In order to promote the development of intelligent agriculture and realize intelligent mechanical picking, it provides effective visual information.https://ieeexplore.ieee.org/document/10374360/Feature excitationbroad learning systemxanthoceras sorbifolium fruitimage classification |
| spellingShingle | Zhang Dan Liu Zuchen Cheng Liying Li Tieshan Gu Liru Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System IEEE Access Feature excitation broad learning system xanthoceras sorbifolium fruit image classification |
| title | Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System |
| title_full | Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System |
| title_fullStr | Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System |
| title_full_unstemmed | Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System |
| title_short | Early Detection of Ripeness for the Picking of Xanthoceras Sorbifolium Using Feature Excitation-Based Broad Learning System |
| title_sort | early detection of ripeness for the picking of xanthoceras sorbifolium using feature excitation based broad learning system |
| topic | Feature excitation broad learning system xanthoceras sorbifolium fruit image classification |
| url | https://ieeexplore.ieee.org/document/10374360/ |
| work_keys_str_mv | AT zhangdan earlydetectionofripenessforthepickingofxanthocerassorbifoliumusingfeatureexcitationbasedbroadlearningsystem AT liuzuchen earlydetectionofripenessforthepickingofxanthocerassorbifoliumusingfeatureexcitationbasedbroadlearningsystem AT chengliying earlydetectionofripenessforthepickingofxanthocerassorbifoliumusingfeatureexcitationbasedbroadlearningsystem AT litieshan earlydetectionofripenessforthepickingofxanthocerassorbifoliumusingfeatureexcitationbasedbroadlearningsystem AT guliru earlydetectionofripenessforthepickingofxanthocerassorbifoliumusingfeatureexcitationbasedbroadlearningsystem |