Detecting Septoria Leaf-Spot Disease in Tomato Plants Using Shifted Window Transformer Model.

Tomato (Solanum lycopersicum) cultivation plays a critical role in ensuring food security and economic stability in many parts of the world. However, productivity is often hindered by fungal infections, notably Septoria Leaf Spot, caused by Septoria lycopersici. This disease significantly reduces crop yields by damaging the foliage and accelerating premature defoliation. Timely detection and diagnosis are essential for effective intervention. In this study, we present a deep learning-based approach for automated identification of Septoria Leaf Spot using the Shifted Window Transformer (Swin Transformer), a hierarchical vision transformer architecture known for its balance of computational efficiency and high accuracy in image classification tasks.
The research followed a structured quantitative methodology encompassing model design, data acquisition, training, and performance evaluation. A publicly available dataset sourced from Kaggle, comprising annotated images of healthy and infected tomato leaves, was used for model development. Preprocessing steps included image resizing, normalization, denoising, and data augmentation techniques such as flipping, brightness adjustment, and rotation.
The Swin Transformer model achieved an accuracy of 93.18%, a precision score of 0.92, and an AUC-ROC of 90.91% on the test set, outperforming conventional CNN models like ResNet-50 and VGG16. These results validate the model’s strong generalization capability and its potential use in smart agricultural applications. The study also emphasizes the architectural advantages of the Swin Transformer in extracting both local and global features critical to plant disease identification.
Nonetheless, the exclusive use of a Kaggle dataset introduces limitations, particularly in representing real-world variability. The paper recommends additional validation using field-captured images under diverse conditions to improve robustness. The findings highlight the promise of attention-based models for early and accurate plant disease detection, potentially contributing to increased agricultural productivity and sustainable farming practices.

Deep Learning, Swin Transformer, Tomato Disease Detection, Septoria Leaf Spot, Agricultural AI

1. O. Agarwala, A. Singh, S. Arjaria, A. Sinha, and S. Gupta, "ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network," Elsevier Journal, vol. 167, pp. 293–301, 2020. [Google Scholar] [Crossref]

2. M. Y. Ali, "Nutritional Composition and Bioactive Compounds in Tomatoes and Their Impact on Human Health and Disease," MDPI, 2020. [Online].Available:https://dx.doi.org/10.3390/foods1001005 [Google Scholar] [Crossref]

3. H. Y. Bayram, H. Bingol, and B. Alatas, "Hybrid Deep Model for Automated Detection of Tomato Leaf Diseases," IIETA, vol. 39, Oct. 2022. [Online]. Available: https://doi.org/10.18280/ts.390537 [Google Scholar] [Crossref]

4. E. J. Collins, C. Bowyer, A. Tsouza, and M. Chopra, "An Extensive Review of the Associated Health Impact of Tomatoes and Factors That Can Affect Their Cultivation," MDPI Biology, 2022. [Google Scholar] [Crossref]

5. H. E. David, K. Ramalakshmi, R. Venkatesan, and G. Hemalatha, "Tomato Leaf Disease Detection Using Smart Intelligent Computing and Communication Technology," 2021. [Online]. Available: https://doi.org/10.3233/APC210108 [Google Scholar] [Crossref]

6. G. Fenu and F. M. Malloci, "Forecasting Plant and Crop Disease: An Explorative Study on Current Algorithm," MDPI Big Data and Cognitive Computing, vol. 5, no. 1, 2020. [Google Scholar] [Crossref]

7. O. O. Fredrick, O. O. Benson, and M. M. Moses, "Tomato Cultivation and Farmers’ Knowledge on Disease Management," Asian Journal of Agricultural and Horticultural Research, vol. 9, pp. 66–80, 2022. [Google Scholar] [Crossref]

8. M. Tiwari, A. Sharma, and R. Gupta, "Tomato diseases detection using vision transformer with residual attention," Journal of Agricultural AI Research, vol. 5, no. 2, pp. 34–46, 2023. [Google Scholar] [Crossref]

9. S. M. N. Ashraf, R. Khan, and M. Javed, "SynthEnsemble: Hybrid models for plant disease classification using CNNs and transformers," IEEE Access, vol. 11, pp. 11234–11245, 2023. [Google Scholar] [Crossref]

10. W.-C. Yong, F. Li, and J. Tang, "Leaf condition analysis using Vision Transformers for plant health monitoring," Agricultural AI Review, vol. 2, no. 1, pp. 17–30, 2023. [Google Scholar] [Crossref]

11. Z. Liu et al., "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows," arXiv preprint arXiv:2103.14030, 2021. [Google Scholar] [Crossref]

12. A. Dosovitskiy et al., "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale," arXiv preprint arXiv:2010.11929, 2020. [Google Scholar] [Crossref]

13. J. Tran, J.-W. Choi, T.-T. H. Le and J. W. Kim, "A comparative study of deep CNN in forecasting and classifying the Macronutrient deficiencies on the development of tomato plant," MDPI, 2019. doi:10.3390/app9081601 [Google Scholar] [Crossref]

14. W. Xinming, T. S. Hong, A. B. M. Arifflin, and M. I. S. Ismail, "Comparative study on leaf disease identification using Yolo v4 and Yolo," 2023. [Google Scholar] [Crossref]

15. B. Gardle, K. Azezew, and S. Asemie, "Image-based Tomato Disease Identification Using Convolutional Neural Network," Indian Journal of Science and Technology, vol. 14, pp. 3126–3132, 2021. [Google Scholar] [Crossref]

16. P. M. Kwabena, A. B. Weyori, and A. A. Mighty, "Gabor Capsule Network for Plant Disease Detection," ResearchGate, 2020. [Online]. Available: https://www.researchgate.net/publication/345154332_Gabor_Capsule_Network_for_Plant_Disease_Detection [Google Scholar] [Crossref]

17. J. Lu, L. Tan, and H. Jiang, "Review on Convolutional Neural Network (CNN) applied to plant leaf disease classification," MDPI Agriculture, vol. 11, no. 707, 2021. [Google Scholar] [Crossref]

18. C. M. Mothapo, T. Dube, E. Abdel-Rahman, and M. Sibanda, "Progress in the use of geospatial and remote sensing technologies in the assessment and monitoring of the tomato crop diseases," GeoJournal, vol. 37, pp. 4784–4804, 2022. [Google Scholar] [Crossref]

19. D. A. Natarajan, M. M. Babitha, and D. S. Kumar, "Detection of disease in tomato plant using Deep Learning Techniques," ResearchGate, 2020. [Google Scholar] [Crossref]

20. M. S. Alzahrani and F. W. Alsaade, "ViT-SmartAgri: Vision Transformer and Smartphone-Based Plant Disease Detection for Smart Agriculture," 2023. [Google Scholar] [Crossref]

21. H. Li, S. Li, J. Yu, Y. Han, and A. Dong, "A Deep Features Extraction Model Based on the Transfer Learning Model and Vision Transformer ‘TLMViT’ for Plant Disease Classification," 2021. [Google Scholar] [Crossref]

22. M. Tabbakh and S. S. Barpanda, "Transform and Deep Learning Algorithms for the Early Detection and Recognition of Tomato Leaf Disease," 2023. [Google Scholar] [Crossref]

23. U. Barman et al., "Convolution Network Enlightened Transformer for Regional Crop Disease Classification," 2024. [Google Scholar] [Crossref]

24. Y. Wang, Y. Chen, and D. Wang, "Tomato Diseases Detection Using Vision Transformer with Residual L1-Norm Attention and Deep Neural Networks," 2023. [Google Scholar] [Crossref]

25. County Government of Kirinyaga, "Governor Waiguru opens first exclusive tomato market as county supports farmers to upscale tomato farming," Aug. 19, 2023. [Online]. Available: https://kirinyaga.go.ke/news-events/. [Google Scholar] [Crossref]