FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement
With the rapid development of seed research, understanding the external structure and characteristics of plants has become essential. Seed coat thickness plays a key role in assessing seed quality in seed reproduction, storage, processing, and research. However, traditional manual measurement method...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Cogent Food & Agriculture |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/23311932.2024.2424928 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850247653596594176 |
|---|---|
| author | Zhikun Zhang Qin Xu Haojie Shi Guangwu Zhao Lu Gao Tao Wang Guosong Gu Liangquan Jia |
| author_facet | Zhikun Zhang Qin Xu Haojie Shi Guangwu Zhao Lu Gao Tao Wang Guosong Gu Liangquan Jia |
| author_sort | Zhikun Zhang |
| collection | DOAJ |
| description | With the rapid development of seed research, understanding the external structure and characteristics of plants has become essential. Seed coat thickness plays a key role in assessing seed quality in seed reproduction, storage, processing, and research. However, traditional manual measurement methods are labor-intensive, subjective bias, and measurement errors. To solve this problem , we propose an efficient and universal deep learning method, FSUNet. Base on the UNet model, FSUNet introduces a new Full-Scale Information Fusion module (FSIF), adopting 7 × 7 depth-wise separable convolutions and point convolutions to capture remote information, and designs the MConv module. The FSUNet model has 5.109 M parameters, only 14.79% of the UNet model. This research validated the method with a self-constructed corn seed coat segmentation dataset. FSUNet achieved segmentation results of 69.37%, 67.80%, 83.85%, and 85.40% on the self-constructed dataset and the three public datasets, respectively, which are 0.24%, 1.95%, 1.51%, and 0.73% higher than those of the UNet model. Compared to other recent lightweight models like CMUNext, FSUNet shows significant advantages. In addition, we also provide a seed coat thickness measurement algorithm that can obtain stable and accurate measurement results. Through our method, the measurement efficiency and accuracy of seed coat thickness can be significantly improved, providing strong tools and technical support for plant seed research. |
| format | Article |
| id | doaj-art-0694c5fc7e124b63a3e782bf54faf521 |
| institution | OA Journals |
| issn | 2331-1932 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Cogent Food & Agriculture |
| spelling | doaj-art-0694c5fc7e124b63a3e782bf54faf5212025-08-20T01:58:52ZengTaylor & Francis GroupCogent Food & Agriculture2331-19322024-12-0110110.1080/23311932.2024.2424928FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurementZhikun Zhang0Qin Xu1Haojie Shi2Guangwu Zhao3Lu Gao4Tao Wang5Guosong Gu6Liangquan Jia7School of Information Engineering, Huzhou University, Huzhou, Zhejiang, ChinaSchool of Information Engineering, Huzhou University, Huzhou, Zhejiang, ChinaCollege of Modern Agriculture, Zhejiang A&F University, Hangzhou, ChinaCollege of Modern Agriculture, Zhejiang A&F University, Hangzhou, ChinaSchool of Information Engineering, Huzhou University, Huzhou, Zhejiang, ChinaSchool of Information Engineering, Huzhou University, Huzhou, Zhejiang, ChinaSchool of Information Engineering, Jiaxing University, Jiaxing, Zhejiang, ChinaSchool of Information Engineering, Huzhou University, Huzhou, Zhejiang, ChinaWith the rapid development of seed research, understanding the external structure and characteristics of plants has become essential. Seed coat thickness plays a key role in assessing seed quality in seed reproduction, storage, processing, and research. However, traditional manual measurement methods are labor-intensive, subjective bias, and measurement errors. To solve this problem , we propose an efficient and universal deep learning method, FSUNet. Base on the UNet model, FSUNet introduces a new Full-Scale Information Fusion module (FSIF), adopting 7 × 7 depth-wise separable convolutions and point convolutions to capture remote information, and designs the MConv module. The FSUNet model has 5.109 M parameters, only 14.79% of the UNet model. This research validated the method with a self-constructed corn seed coat segmentation dataset. FSUNet achieved segmentation results of 69.37%, 67.80%, 83.85%, and 85.40% on the self-constructed dataset and the three public datasets, respectively, which are 0.24%, 1.95%, 1.51%, and 0.73% higher than those of the UNet model. Compared to other recent lightweight models like CMUNext, FSUNet shows significant advantages. In addition, we also provide a seed coat thickness measurement algorithm that can obtain stable and accurate measurement results. Through our method, the measurement efficiency and accuracy of seed coat thickness can be significantly improved, providing strong tools and technical support for plant seed research.https://www.tandfonline.com/doi/10.1080/23311932.2024.2424928Plant seed researchseed coat thicknessFSIFMConvFSUNetPlant Biotechnology |
| spellingShingle | Zhikun Zhang Qin Xu Haojie Shi Guangwu Zhao Lu Gao Tao Wang Guosong Gu Liangquan Jia FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement Cogent Food & Agriculture Plant seed research seed coat thickness FSIF MConv FSUNet Plant Biotechnology |
| title | FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement |
| title_full | FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement |
| title_fullStr | FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement |
| title_full_unstemmed | FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement |
| title_short | FSUNet: lightweight full-scale information fusion UNet for seed coat thickness measurement |
| title_sort | fsunet lightweight full scale information fusion unet for seed coat thickness measurement |
| topic | Plant seed research seed coat thickness FSIF MConv FSUNet Plant Biotechnology |
| url | https://www.tandfonline.com/doi/10.1080/23311932.2024.2424928 |
| work_keys_str_mv | AT zhikunzhang fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT qinxu fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT haojieshi fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT guangwuzhao fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT lugao fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT taowang fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT guosonggu fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement AT liangquanjia fsunetlightweightfullscaleinformationfusionunetforseedcoatthicknessmeasurement |