Plant Diseased Lesion Image Segmentation and Recognition Based on Improved Multi-Scale Attention Net
Source abstract
Abstract
Fallen leaf disease can lead to a decrease in leaf area, a decrease in photosynthetic products, insufficient accumulation of fruit sugar, poor coloring and flavor, and a large number of fruits developing sunburn. To address the aforementioned issue, this article introduces a deep learning algorithm designed for the segmentation and recognition of agricultural disease images, particularly those involving leaf lesions. The essence of this algorithm lies in enhancing the Multi-scale Attention Net (MA-Net) encoder and attention mechanism to improve the model’s performance when processing agricultural disease images. Firstly, an analysis was conducted on MA-Net, and its limitations were identified. Compared to res-block, Mix Vision Transformer (MiT) consumes relatively less time during the training process, can better capture global and contextual information in images, and has better robustness and scalability. Then, the feature extraction parts of different networks were used as encoders to join the MA-Net network. Compared to a Position-wise Attention Block (PAB), which has higher computational complexity and requires a larger amount of computing resources, Effective Channel Attention net (ECANet) reduces the number of model parameters and computation by learning the correlation between channels, as well as having a better denoising ability. The experimental results show that the proposed solution has high accuracy and stability in agricultural disease image segmentation and recognition. The mean Intersection over Union (mIoU) is 98.1%, which is 0.2% higher than traditional MA-Net; Dice Loss is 0.9%, which is 0.1% lower than traditional MA-Net.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Technology and Security Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information, Graduate School of Xi’an Engineering University, Lintong Campus, Xi’an 710000, China
References (36)
Show source-provided references
1. Xiaolei, B., Yuehua, W., and Hanbing, Z. (2017). Development of Agriculture and Forestry and Food Safety, Jilin People’s Publishing House.
2. Xu, L., Zhao, Y., Liu, P., Ban, X., Zhao, J., and Dai, F. (2023, January 25–28). Application of an improved lightweight YOLOv5 model to wheat stripe rust detection. Proceedings of the 2023 11th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), Wuhan, China.10.1109/Agro-Geoinformatics59224.2023.10233444 ↗
3. Grape disease image recognition method based on support vector machine
4. Research on Apple Disease Identification Technology Based on Mobile Phone Image Analysis
5. Kaur, R., and Kang, S.S. (2015, January 1–2). An enhancement in classifier support vector machine to improve plant disease detection. Proceedings of the 2015 IEEE 3rd International Conference on MOOCs, Innovation and Technology in Education (MITE), Amritsar, India.10.1109/MITE.2015.7375303 ↗
6. Classification method of rice blast disease severity based on hyperspectral imaging
7. Padol, P.B., and Yadav, A.A. (2016, January 26–30). SVM classifier based grape leaf disease detection. Proceedings of the 2016 Conference on Advances in Signal Processing (CASP), Pune, India.10.1109/CASP.2016.7746160 ↗
8. Detection of wine grape leaves based on HOG
9. Islam, M., Dinh, A., Wahid, K., and Bhowmik, P. (May, January 30). Detection of potato diseases using image segmentation and multiclass support vector machine. Proceedings of the 2017 IEEE 30th Canadian conference on electrical and computer engineering (CCECE), Windsor, ON, Canada.10.1109/CCECE.2017.7946594 ↗
10. Detection of IKSVM rice blast spores based on HOG characteristics
11. SLIC_SVM based leaf diseases saliency map extraction of tea plant10.1016/j.compag.2018.12.042 ↗
12. Research on identification of barley diseases based on support vector machines
13. Reducing the Dimensionality of Data with Neural Networks10.1126/science.1127647 ↗
14. Deep neural networks based recognition of plant diseases by leaf image classification10.1155/2016/3289801 ↗
15. Deep learning for tomato diseases: Classification and symptoms visualization10.1080/08839514.2017.1315516 ↗
16. Adaptive feature fusion and fast recognition of typical potato disease images
17. Veeraballi, R.K., Nagugari, M.S., Annavarapu, C.S.R., and Gownipuram, E.V. (2018, January 6–8). Deep Learning Based Approach for Classification and Detection of Papaya Leaf Diseases. Proceedings of the International Conference on Intelligent Systems Design and Applications, Vellore, India.10.1007/978-3-030-16657-1_27 ↗
18. Identification of maize leaf diseases using improved deep convolutional neural networks10.1109/ACCESS.2018.2844405 ↗
19. Silva Abade, A., Almeida, A.P.G.S., and Barros Vidal, F. (2019, January 25–27). Plant Diseases Recognition from Digital Images using Multichannel Convolutional Neural Networks. Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (5: VISAPP), Prague, Czech Republic.10.5220/0007383900002108 ↗
20. Fine grained tomato disease recognition based on attention residual mechanism
21. Performance analysis of deep learning CNN models for disease detection in plants using image segmentation
22. Image recognition of four rice leaf diseases based on deep learning and support vector machine10.1016/j.compag.2020.105824 ↗
23. Leaf Disease Identification Based on Fusion Channel Information Attention Network
24. Real time detection of inter-row ryegrass in wheat farms using deep learning10.1016/j.biosystemseng.2021.01.019 ↗
25. A segmentation algorithm for corn leaf lesions based on U-Net
26. Real time semantic segmentation model for crop disease leaves based on group attention module
27. Data augmentation for deep learning based semantic segmentation and crop-weed classification in agricultural robotics10.1016/j.compag.2021.106418 ↗
28. Recognition of rice leaf diseases and wheat leaf diseases based on multi-task deep transfer learning10.1016/j.compag.2021.106184 ↗
29. Identification of corn diseases in complex backgrounds based on improved convolutional neural networks
30. Leaf disease identification and mobile application based on transfer learning
31. Corn disease image recognition based on attention mechanism asymmetric residual network and transfer learning
32. A tomato disease recognition method based on multi-scale and attention mechanism
33. GoogLeNet Orchard Disease and Pest Identification and Grading Based on Transfer Learning
34. Identification of Apple Leaf Diseases Based on Improved Convolutional Neural Networks
35. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv.
36. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (1997, January 17–19). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA.