Early Detection of Crop Diseases Using Deep Learning Models

Crop diseases pose a serious threat to global food security by significantly reducing agricultural yield and economic stability. Although recent advances in deep learning have enabled automated crop disease detection with high accuracy, most existing systems focus primarily on leaf-based classification and fail to provide disease severity assessment, which is crucial for real-world agricultural decision-making. This paper presents a deep learning powered system for early detection of crop diseases that integrates HSV color-space segmentation with convolutional neural networks (CNNs) to detect diseases affecting both leaves and fruits while quantitatively estimating disease severity. The proposed system enhances lesion visibility through HSV-based pre-processing and isolates infected regions prior to classification using a transfer-learning-based EfficientNet-B4 architecture. Disease severity is estimated by calculating the percentage of infected tissue and categorizing it into mild (1–10%), moderate (11–25%), and severe (>25%) levels. Extensive data augmentation techniques are employed to improve robustness under varying illumination and real-field conditions. Experimental evaluation conducted on benchmark datasets and real-field images achieved classification accuracies of 99.18% for leaf diseases, 96.47% for fruit diseases, and 83.33% under field conditions. A web-based interface enables real-time disease diagnosis with visual lesion interpretation and severity reporting. The results demonstrate that the proposed system is accurate, interpretable, and suitable for deployment in precision agriculture for early disease management.

crop disease detection, deep learning, convolutional neural networks, HSV segmentation, disease severity estimation, precision agriculture

1. Zhao, Y., Li, X., & Wang, H. (2023). Deep learning for plant disease detection: A comprehensive review. Computers and Electronics in Agriculture, 206, 107613. [Google Scholar] [Crossref]

2. Sanida, L., Glaroudis, D., & Papadopoulos, T. (2023). Lightweight convolutional neural networks for real-time plant disease detection on mobile devices. Computers and Electronics in Agriculture, 202, 107350. [Google Scholar] [Crossref]

3. Shoaib, M., Khan, A., & Rauf, H. T. (2023). Segmentation-driven plant leaf disease detection and severity estimation using deep learning. Journal of Plant Pathology, 105(3), 587–600. [Google Scholar] [Crossref]

4. Anonymous. (2024). Severity Estimation of Plant Leaf Diseases Using Segmentation Techniques. International Journal of Computer Applications in Agriculture, 15(2), 45–53. [Google Scholar] [Crossref]

5. Elakya, V., & Manoranjitham, R. (2024). Deep learning framework for detection and severity classification of plant leaf diseases using CNN and U-Net segmentation. Journal of Agricultural Informatics, 15(1), 22–35. [Google Scholar] [Crossref]

6. Faye, R., Diop, M., & Sow, A. (2025). Severity analysis of mango fruit diseases using segmentation and CNN-based models. Precision Agriculture, 26(4), 455–470. [Google Scholar] [Crossref]

7. Johari, P.F., Arifin, N., Muzaki, M. & Utama, M.S.A. (2025). Corn Leaf Diseases Classification Using CNN with GLCM, HSV, and L*a*b* Features. Jurnal Teknik Informatika (Jutif), 6(2), 709-722. [Google Scholar] [Crossref]

8. Maimaitijiang, M., Sagan, V., & Sidike, P. (2017). Vegetation indices for plant disease detection using multispectral imagery. Remote Sensing, 9(7), 667. [Google Scholar] [Crossref]

9. Ghafar, A., Hussain, M., & Shah, S. (2024). Visualization and performance evaluation of deep learning models for plant disease detection using YOLOv8. Computers and Electronics in Agriculture, 215, 108274. [Google Scholar] [Crossref]

10. Anand Kumar, A., Monga, H. P., Brahma, T., Kalra, S., & Sherif, N. (2025). Mobile friendly deep learning for plant disease detection: A lightweight CNN benchmark across 101 classes of 33 crops. arXiv preprint arXiv:2508.10817. [Google Scholar] [Crossref]

11. Boyapati, S., & Vigneshwari, S. (2024). Revolutionizing food security: Unleashing the power of VGG16, EfficientNet, and ResNet34 in plant disease classification. African Journal of Biomedical Research, 27(4S), 6131-6142. 75 [Google Scholar] [Crossref]

12. Bhilare, A., Swain, D., & Patel, N. (2023). Comparative analysis of deep learning models for accurate detection of plant diseases: A comprehensive survey. EAI Endorsed Transactions on Internet of Things, 10(1). [Google Scholar] [Crossref]

13. Khand gale, H. P., Patil, S., Gavali, V. S., Chavan, S. V., Halkarnikar, P. P., & Meshram, P. A. (2025). Design and implementation of FourCropNet: A CNN-based system for efficient multi-crop disease detection and management. arXiv preprint arXiv:2503.08348. [Google Scholar] [Crossref]

14. Sun, Y., Ning, L., Zhao, B., & Yan, J. (2024). Tomato leaf disease classification by combining EfficientNetV2 and a Swin Transformer. Applied Sciences, 14(17), 7472. [Google Scholar] [Crossref]

15. Nandi, R. N., Palash, A. H., Siddique, N., & Zilani, M. G. (2022). Device-friendly guava fruit and leaf disease detection using deep learning. arXiv preprint arXiv:2209.12557. [Google Scholar] [Crossref]

16. Kaur, K., & Bansal, K. (2024). Enhancing plant disease detection using advanced deep learning models. Indian Journal of Science and Technology, 17(17), 1755-1766. [Google Scholar] [Crossref]

17. Henan Institute of Science and Technology. (2024). An effective image classification method for plant diseases with improved channel attention mechanism aECAnet based on deep learning. Symmetry, 16(4), 451. [Google Scholar] [Crossref]

18. Salvi, V., & Bhairnallykar, S. (2024). Optimizing plant leaf disease detection: A comparative study of deep learning models. Journal of Propulsion Technology, 45(4). [Google Scholar] [Crossref]

19. Aristan, T., & Kusuma, G. P. (2023). Evaluation of CNN models in identifying plant diseases on a mobile device. Research in Artificial Intelligence and Applications, 37(2), 221 228. [Google Scholar] [Crossref]

20. Nyawose, T. (2025). A review on the detection of plant disease using machine learning and deep learning. Vision, 11(10), 326. [Google Scholar] [Crossref]

21. Shafay, M., Hassan, T., Owais, M., Hussain, I., Khawaja, S. G., & Seneviratne, L. (2025). Recent advances in plant disease detection: Challenges and opportunities. Plant Methods, 21, 140. [Google Scholar] [Crossref]

22. Li, Z., Zhang, X., & Yang, P. (2024). Deep learning and computer vision in plant disease detection: A comprehensive survey. Artificial Intelligence Review, 57(4), 1–27. [Google Scholar] [Crossref]

23. Ahmad, N., Rahman, T., & Qureshi, A. (2024). Color space-based crop disease classification using HSV and Lab features in deep CNN frameworks. Computers and Electronics in Agriculture, 214, 108215. [Google Scholar] [Crossref]

24. Rani, M., Sharma, D., & Thakur, P. (2025). A survey to identify plant leaf diseases by feature extraction and deep learning models. International Journal of Agricultural Technology, 21(1), 78–91. 76 [Google Scholar] [Crossref]

25. Patil, K., & More, S. (2024). Convolutional neural networks-based paddy leaf disease detection using HSV color segmentation and data augmentation. International Journal of Recent Advances in Science and Engineering, 12(6), 87–94. [Google Scholar] [Crossref]

26. Das, A., & Banerjee, S. (2024). A robust ensemble model for multi-crop plant disease detection using hybrid CNNs and attention mechanisms. Sensors, 24(5), 159. [Google Scholar] [Crossref]

27. Patel, R., & Mehta, V. (2025). Potato plant disease detection leveraging hybrid EfficientNetV2B3 and Vision Transformer model. BMC Plant Biology, 25(2), 335–347. [Google Scholar] [Crossref]

28. Nandi, R. N., Palash, A. H., & Siddique, N. (2024). Mobile-based fruit and leaf disease recognition using lightweight CNN models. Computational Agriculture Journal, 18(3), 201 210. [Google Scholar] [Crossref]

29. Kumar, P., & Verma, R. (2025). Deep CNN architectures for real-time crop disease detection: A comparative study on tomato and maize datasets. International Journal of Artificial Intelligence and Data Science, 9(1), 44–58. “Media Statement Gross Domestic Product (GDP) By State”, Department of Statistics Malaysia, 2024. [Google Scholar] [Crossref]

• Breeding for a Greener Future: Selective Breeding and Crossbreeding Approaches to Minimize Methane Emissions in Ruminant Livestock
• Determinants of Adoption of Post-Harvest Losses Prevention Techniques among Banana/Plantain Marketers in Lagos State, Nigeria
• Enhancing Rice Yield Prediction Using UAV-Based Multispectral Imaging and Machine Learning Algorithms
• Seed-Borne Fungi of Groundnuts (Arachis Hypogaea) and Their Management with Ginger (Zingiber Officinale) Extract In Makurdi, Nigeria
• The Influence of Landforms and Slope on Agricultural Cropping Patterns in Chhatrapati Sambhajinagar District