Mehdhar S. A. M. Al-gaashani

Using a resnet50 with a kernel attention mechanism for rice disease diagnosis

• Authors Details :  
• Mehdhar S. A. M. Al-gaashani ,  
• Nagwan Abdel Samee ,  
• Rana Alnashwan And Mashael Khayya ,  
• Mohammed Saleh Ali Muthanna

Journal title : Life

Publisher : MDPI AG

Online ISSN : 2075-1729

Page Number : 1277

Journal volume : 13

Journal issue : 6

319 Views Original Article

The domestication of animals and cultivation of crops have been essential to human development throughout history, with the agricultural sector playing a pivotal role. Insufficient nutrition often leads to plant diseases, such as those affecting rice crops, resulting in yield losses of 20-40% of total production. These losses carry significant global economic consequences. Timely disease diagnosis is critical for implementing effective treatments and mitigating financial losses. However, despite technological advancements, rice disease diagnosis primarily depends on manual methods. In this study, we present a novel Self-Attention Network (SANET) based on the ResNet50 architecture, incorporating a kernel attention mechanism for accurate AI-assisted rice disease classification. We employ attention modules to extract contextual dependencies within images, focusing on essential features for disease identification. Using a publicly available rice disease dataset comprising four classes (three disease types and healthy leaves), we conducted cross-validated classification experiments to evaluate our proposed model. The results reveal that the attention-based mechanism effectively guides the Convolutional Neural Network (CNN) in learning valuable features, resulting in accurate image classification and reduced performance variation compared to state-of-the-art methods. Our SANET model achieved a test set accuracy of 98.71%, surpassing current leading models. These findings highlight the potential for widespread AI adoption in agricultural disease diagnosis and management, ultimately enhancing efficiency and effectiveness within the sector.

Article DOI & Crossmark Data

DOI : https://doi.org/10.3390/life13061277

Article Subject Details

• Artificial Intelligence
• Biomedical Engineering
• Computer Science
• Computer Science Applications

Article Keywords Details

• Rice disease classification; self-attention mechanism; agriculture imaging

Article File

Full Text PDF

Article References

• (1). Agrios, G. (2005). Plant Pathology, Elsevier Academic Press. [5th ed].
• (2). 10.1080/24725579.2019.1646358
• (3). Lu, H., Wang, H., Zhang, Q., Won, D., and Yoon, S.W. (2018, January 4–7). A dual-tree complex wavelet transform based convolutional neural network for human thyroid medical image segmentation. Proceedings of the 2018 IEEE International Conference on Healthcare Informatics (ICHI), New York, NY, USA.
• (4). Zhang, Q., Wang, H., Lu, H., Won, D., and Yoon, S.W. (2018, January 4–7). Medical image synthesis with generative adversarial networks for tissue recognition. Proceedings of the 2018 IEEE International Conference on Healthcare Informatics (ICHI), New York, NY, USA.
• (5). 10.1016/j.cj.2017.05.004
• (6). 10.1016/j.asoc.2019.105933
• (7). 10.1007/s00521-022-07793-2
• (8). 10.1016/j.compeleceng.2022.108492
• (9). 10.1016/j.compag.2022.107543
• (10). Jiang, M., Feng, C., Fang, X., Huang, Q., Zhang, C., and Shi, X. (2023). Rice Disease Identification Method Based on Attention Mechanism and Deep Dense Network. Electronics, 12.
• (11). Zhang, H. (2022, January 25–27). Attention-based feature enhancement for rice leaf disease recognition. Proceedings of the 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), Zhuhai, China.
• (12). Goceri, E., and Gooya, A. (2018, January 3–6). On the importance of batch size for deep learning. Proceedings of the International Conference on Mathematics (ICOMATH2018), An Istanbul Meeting for World Mathematicians, Istanbul, Turkey.
• (13). 10.1109/ACCESS.2018.2810849
• (14). Zeiler, M.D., and Fergus, R. (2014, January 6–12). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.
• (15). 10.1016/j.neucom.2017.06.023
• (16). Rafeed Rahman, C., Saha Arko, P., Eunus Ali, M., Khan MA, I., Hasan Apon, S., Nowrin, F., and Wasif, A. (2018). Identification and recognition of rice diseases and pests using convolutional neural networks. arXiv.
• (17). Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
• (18). Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18–22). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.
• (19). Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv.
• (20). 10.1038/s41598-019-38966-0
• (21). 10.1109/JIOT.2019.2947624
• (22). 10.1016/j.compag.2018.12.006
• (23). Duong-Trung, N., Quach, L.-D., Nguyen, M.-H., and Nguyen, C.-N. (2019, January 25–28). Classification of grain discoloration via transfer learning and convolutional neural networks. Proceedings of the 3rd International Conference on Machine Learning and Soft Computing, Da Lat, Vietnam.
• (24). 10.5194/isprs-archives-XLII-3-W6-631-2019
• (25). 10.1016/j.compag.2016.01.008
• (26). Tai, H.-T., Tran-Van, N.-Y., and Le, K.-H. (2021, January 14–16). Artifcial cognition for early leaf disease detection using vision transformers. Proceedings of the 2021 International Conference on Advanced Technologies for Communications (ATC), Virtual.
• (27). Reedha, R., Dericquebourg, E., Canals, R., and Hafane, A. (2022). Transformer neural network for weed and crop classifcation of high resolution UAV images. Remote Sens., 14.
• (28). Wu, S., Sun, Y., and Huang, H. (2021, January 10–12). Multi-granularity feature extraction based on vision transformer for tomato leaf disease recognition. Proceedings of the 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST), Guangzhou, China.
• (29). He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
• (30). 10.1016/j.eswa.2021.114770
• (31). Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
• (32). Tsai YH, H., Bai, S., Yamada, M., Morency, L.P., and Salakhutdinov, R. (2019). Transformer Dissection: A Unified Understanding of Transformer’s Attention via the Lens of Kernel. arXiv.
• (33). Do, H.M. (2023, May 19). Rice Diseases Image Dataset: An Image Dataset for Rice and Its Diseases. Available online: https://www.kaggle.com/datasets/minhhuy2810/rice-diseases-image-dataset.
• (34). Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
• (35). Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.
• (36). Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
• (37). Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.

---

More Article by Mehdhar S. A. M. Al-Gaashani