YOLO-Based Rice Disease Detection For Precision Agriculture

Author

Swejal Wasnik, Niharika Rokade, Khushbu Bagade, Gayatri Padole, Vaishnavi Vaidya, Prof. Yogesh B. Malode


Abstract

 Agricultural productivity is frequently reduced by leaf diseases, and their symptoms are difficult for non-specialists to tell apart by visual inspection. This paper presents LeafScan, an AI-based plant health detection system that analyses images of plant leaves and returns preliminary information about the plant category and its possible health condition. The system is organised into three cooperating layers: a React and Vite presentation layer offering registration, login, a dashboard, image upload with preview and a scan-history view; a Python FastAPI service layer that handles token-based authentication, receives uploaded images and exposes a scan-history API; and persistence in SQLite accessed through SQLAlchemy. YOLO11 classification model trained on a rice-leaf dataset of 5,932 images covering Bacterial Blight, Blast, Brown Spot . A local vision-language model, qwen2.5vl:3b served through Ollama, was explored for generating explanatory descriptions without sending images to a cloud service. The paper documents the requirements, design, implementation and testing status, and records the current limitations: the scan API still produced runtime errors in testing, the class mapping and prediction confidence of the models require validation, and the local vision-language model produced inconsistent output on some requests. Final accuracy figures are therefore not claimed. LeafScan is intended as a decision-support tool for preliminary screening and not as a replacement for professional agricultural diagnosis.


Keywords

Plant Disease Detection, Rice Leaf Disease, EfficientNet-B0, YOLO11, FastAPI, React, SQLite, Ollama, Vision-Language Model, Deep Learning.



Full Text:

Download Paper PDF


References


  1. Agrawal, A. Suri, and K. Verma, "An integrated deep learning framework for plant disease detection, severity analysis, and AI-based cure recommendation," in Proc. Conf. Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026), Atlantis Press, Jun. 2026, pp. 125–136, doi: 10.2991/978-94-6239-697-5_12.
  2. Ranjan, O. Tigga, and J. Pal, "A study and analysis of plant leaf disease prediction using deep learning techniques," in Proc. Int. Conf. Emerging Trends and Technologies in Applications of Computer Science (ICETTACS 2026), Atlantis Press, Sep. 2026, pp. 121–132, doi: 10.2991/978-94-6239-799-6_9.
  3. Mahmood, Y. Yu, and R. Anwer, "AgriChain: Visually-grounded expert-verified reasoning for interpretable agricultural vision–language models," in Proc. 15th Language Resources and Evaluation Conf. (LREC), ELRA, 2026.
  4. J. Chaudhary, "An effective deep learning approach to plant disease detection," Undergraduate Conf. Intelligent Computing and Systems (UCICS 2025), Feb. 2025, doi: 10.13140/RG.2.2.18898.67522.
  5. Bai et al., "Qwen2.5-VL technical report," arXiv:2502.13923, 2025.
  6. Ranario et al., "Are vision-language models ready to zero-shot replace supervised classification models in agriculture?," arXiv:2512.15977, Dec. 2025.
  7. I. Ritharson, K. Raimond, X. A. Mary, J. E. Robert, and A. J, "DeepRice: A deep learning and deep feature based classification of rice leaf disease subtypes," Artificial Intelligence in Agriculture, vol. 11, pp. 34–49, Mar. 2024.
  8. Jocher and J. Qiu, "Ultralytics YOLO11," Ultralytics, 2024. [Online]. Available: https://github.com/ultralytics/ultralytics
  9. Wang et al., "Qwen2-VL: Enhancing vision-language model’s perception of the world at any resolution," arXiv:2409.12191, 2024.
  10. Aggarwal, V. Khullar, N. Goyal, A. Singh, A. Tolba, E. B. Thompson, and S. Kumar, "Pre-trained deep neural network-based features selection supported machine learning for rice leaf disease classification," Agriculture, vol. 13, no. 5, p. 936, Apr. 2023, doi: 10.3390/agriculture13050936.
  11. Mustofa, M. M. H. Munna, Y. R. Emon, and M. T. Ahad, "A comprehensive review on plant leaf disease detection using deep learning," arXiv:2308.14087, Aug. 2023.
  12. M. Sudhesh, V. Sowmya, S. Kurian, and O. K. Sikha, "AI based rice leaf disease identification enhanced by dynamic mode decomposition," Engineering Applications of Artificial Intelligence, 2023.
  13. Bruno et al., "Improving plant disease classification by adaptive minimal ensembling," Frontiers in Artificial Intelligence, vol. 5, Sep. 2022, doi: 10.3389/frai.2022.868926.
  14. H. Bui, V. M. Hoang, and N. V. Nguyen, "Enhancing the performance of transferred EfficientNet models in leaf image-based plant disease classification," Journal of Plant Diseases and Protection, 2022.
  15. Ü. Atila, M. Uçar, K. Akyol, and E. Uçar, "Plant leaf disease classification using EfficientNet deep learning model," Ecological Informatics, vol. 61, Art. no. 101182, Mar. 2021.
  16. Dosovitskiy et al., "An image is worth 16x16 words: Transformers for image recognition at scale," in Proc. Int. Conf. Learning Representations (ICLR), 2021.
  17. Tan and Q. V. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," in Proc. 36th Int. Conf. Machine Learning (ICML), PMLR vol. 97, 2019, pp. 6105–6114.
  18. C. Too, L. Yujian, S. Njuki, and L. Yingchun, "A comparative study of fine-tuning deep learning models for plant disease identification," Computers and Electronics in Agriculture, vol. 161, pp. 272–279, Jun. 2019.
  19. Meta Open Source. (n.d.). React documentation. https://react.dev/
  20. (n.d.). Vite documentation. https://vite.dev/guide/
  21. (n.d.). FastAPI documentation. https://fastapi.tiangolo.com/
  22. (n.d.). SQLAlchemy documentation. https://docs.sqlalchemy.org/
  23. (n.d.). PyTorch documentation. https://pytorch.org/docs/stable/index.html
  24. (n.d.). Ollama – run large language and vision-language models locally. https://github.com/ollama/ollama

Share your valuable work from Social Media Buttons