MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments
The accurate prevention and control of pear tree diseases, especially the precise segmentation of leaf diseases, poses a serious challenge to fruit farmers globally. Given the possibility of disease areas being minute with ambiguous boundaries, accurate segmentation becomes difficult. In this study,...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/12/18/3209 |
| _version_ | 1797577838615855104 |
|---|---|
| author | Haoyu Wang Jie Ding Sifan He Cheng Feng Cheng Zhang Guohua Fan Yunzhi Wu Youhua Zhang |
| author_facet | Haoyu Wang Jie Ding Sifan He Cheng Feng Cheng Zhang Guohua Fan Yunzhi Wu Youhua Zhang |
| author_sort | Haoyu Wang |
| collection | DOAJ |
| description | The accurate prevention and control of pear tree diseases, especially the precise segmentation of leaf diseases, poses a serious challenge to fruit farmers globally. Given the possibility of disease areas being minute with ambiguous boundaries, accurate segmentation becomes difficult. In this study, we propose a pear leaf disease segmentation model named MFBP-UNet. It is based on the UNet network architecture and integrates a Multi-scale Feature Extraction (MFE) module and a Tokenized Multilayer Perceptron (BATok-MLP) module with dynamic sparse attention. The MFE enhances the extraction of detail and semantic features, while the BATok-MLP successfully fuses regional and global attention, striking an effective balance in the extraction capabilities of both global and local information. Additionally, we pioneered the use of a diffusion model for data augmentation. By integrating and analyzing different augmentation methods, we further improved the model’s training accuracy and robustness. Experimental results reveal that, compared to other segmentation networks, MFBP-UNet shows a significant improvement across all performance metrics. Specifically, MFBP-UNet achieves scores of 86.15%, 93.53%, 90.89%, and 0.922 on MIoU, MP, MPA, and Dice metrics, marking respective improvements of 5.75%, 5.79%, 1.08%, and 0.074 over the UNet model. These results demonstrate the MFBP-UNet model’s superior performance and generalization capabilities in pear leaf disease segmentation and its inherent potential to address analogous challenges in natural environment segmentation tasks. |
| first_indexed | 2024-03-10T22:13:38Z |
| format | Article |
| id | doaj.art-b434b21048214b0bb6ea5af396f2c110 |
| institution | Directory Open Access Journal |
| issn | 2223-7747 |
| language | English |
| last_indexed | 2024-03-10T22:13:38Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj.art-b434b21048214b0bb6ea5af396f2c1102023-11-19T12:31:37ZengMDPI AGPlants2223-77472023-09-011218320910.3390/plants12183209MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural EnvironmentsHaoyu Wang0Jie Ding1Sifan He2Cheng Feng3Cheng Zhang4Guohua Fan5Yunzhi Wu6Youhua Zhang7School of Information and Computer Science, Anhui Agricultural University, Hefei 230036, ChinaSchool of Information and Computer Science, Anhui Agricultural University, Hefei 230036, ChinaAnhui Provincial Engineering Laboratory for Beidou Precision Agriculture Information, Anhui Agricultural University, Hefei 230036, ChinaAnhui Provincial Engineering Laboratory for Beidou Precision Agriculture Information, Anhui Agricultural University, Hefei 230036, ChinaSchool of Information and Computer Science, Anhui Agricultural University, Hefei 230036, ChinaSchool of Information and Computer Science, Anhui Agricultural University, Hefei 230036, ChinaSchool of Information and Computer Science, Anhui Agricultural University, Hefei 230036, ChinaSchool of Information and Computer Science, Anhui Agricultural University, Hefei 230036, ChinaThe accurate prevention and control of pear tree diseases, especially the precise segmentation of leaf diseases, poses a serious challenge to fruit farmers globally. Given the possibility of disease areas being minute with ambiguous boundaries, accurate segmentation becomes difficult. In this study, we propose a pear leaf disease segmentation model named MFBP-UNet. It is based on the UNet network architecture and integrates a Multi-scale Feature Extraction (MFE) module and a Tokenized Multilayer Perceptron (BATok-MLP) module with dynamic sparse attention. The MFE enhances the extraction of detail and semantic features, while the BATok-MLP successfully fuses regional and global attention, striking an effective balance in the extraction capabilities of both global and local information. Additionally, we pioneered the use of a diffusion model for data augmentation. By integrating and analyzing different augmentation methods, we further improved the model’s training accuracy and robustness. Experimental results reveal that, compared to other segmentation networks, MFBP-UNet shows a significant improvement across all performance metrics. Specifically, MFBP-UNet achieves scores of 86.15%, 93.53%, 90.89%, and 0.922 on MIoU, MP, MPA, and Dice metrics, marking respective improvements of 5.75%, 5.79%, 1.08%, and 0.074 over the UNet model. These results demonstrate the MFBP-UNet model’s superior performance and generalization capabilities in pear leaf disease segmentation and its inherent potential to address analogous challenges in natural environment segmentation tasks.https://www.mdpi.com/2223-7747/12/18/3209pear leaf diseasesegmentation modelmulti-scale feature extractiondiffusion modeldynamic sparse attention mechanismMFBP-UNet |
| spellingShingle | Haoyu Wang Jie Ding Sifan He Cheng Feng Cheng Zhang Guohua Fan Yunzhi Wu Youhua Zhang MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments Plants pear leaf disease segmentation model multi-scale feature extraction diffusion model dynamic sparse attention mechanism MFBP-UNet |
| title | MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments |
| title_full | MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments |
| title_fullStr | MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments |
| title_full_unstemmed | MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments |
| title_short | MFBP-UNet: A Network for Pear Leaf Disease Segmentation in Natural Agricultural Environments |
| title_sort | mfbp unet a network for pear leaf disease segmentation in natural agricultural environments |
| topic | pear leaf disease segmentation model multi-scale feature extraction diffusion model dynamic sparse attention mechanism MFBP-UNet |
| url | https://www.mdpi.com/2223-7747/12/18/3209 |
| work_keys_str_mv | AT haoyuwang mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT jieding mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT sifanhe mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT chengfeng mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT chengzhang mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT guohuafan mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT yunzhiwu mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments AT youhuazhang mfbpunetanetworkforpearleafdiseasesegmentationinnaturalagriculturalenvironments |