Machine Learning-Based Plant Disease Classification Using Leaf Image Features: A Comparative Analysis of Model Performance and Generalization.
Main Article Content
Abstract
Plant diseases have a major impact on crop health and yield, necessitating the development of fast, precise, and automated plant disease identification systems. In this research, a machine learning-based method for identifying plant diseases based on numerical features taken from images of plant leaves is presented. This method investigates the classification of healthy leaves and those infected by Alternaria Alternata, Anthracnose, Bacterial Blight, and Cercospora Leaf Spot by means of six supervised machine learning algorithms: Decision Tree, AdaBoost, Bagged Tree, Naïve Bayes, K- Nearest Neighbour (KNN), and Support Vector Machine (SVM). In total, 13 image features were chosen which are related to statistics and image texture. Those features are: contrast, correlation, energy, homogeneity, mean, standard deviation, entropy, RMS, variance, smoothness, kurtosis, skewness, and inverse difference moment (IDM). The distance of the models’ data acquisition was accomplished according to the train-test scheme. Nonetheless, the follow-up testing generated lower results, confirming the necessity of validation in order to measure model applicability. Among all classifiers tested, SVM offers the best results, achieving 82.2% accuracy in 3-fold cross-validation, 79.6% precision in 4-fold cross-validation, 86.5% accuracy in the case of 25% of holdout validation, and 85.8% results in 35% of holdout validation. The accuracy of both the Weighted KNN and AdaBoost algorithms has been good, too. The conclusion to be drawn from the case study is that SSM yields the most trustworthy classification results in the new theoretical framework. In addition, it should be emphasized that the reliability of the algorithms depends heavily on the thoroughness of validation and that the training data has to be representative to avoid overly optimistic estimates. Lastly, the newly proposed framework has the potential to be further developed with larger and more diverse training databases....
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Kumar, R., Patel, A., & Singh, M. (2024). Advancing real-time plant disease detection: A lightweight deep learning approach and novel dataset for pigeon pea crop. Smart Agricultural Technology, 7, 100408. https://doi.org/10.1016/j.atech.2024.100408
Chen, Y., Li, Z., & Wang, H. (2024). A benchmark dataset for detecting disease in plant leaves: An essential resource for deep learning models [Data set]. Mendeley Data. https://doi.org/10.17632/v46jkbbzv3.1
Patel, J., & Thakkar, H. (2024). Plant disease detection and classification techniques: A comparative study of the performances. Journal of Big Data, 11(5), 1–20. https://doi.org/10.1186/s40537-023-00863-9
Reddy, P., & Sharma, K. (2024). A comprehensive dataset on diseases affecting rose leaves: Identification, symptoms, and control strategies [Data set]. Mendeley Data. https://doi.org/10.17632/hmjtdzkfh3.1
Nguyen, T., & Park, S. (2025). Smart farm rover: Autonomous plant disease detection and classification with machine learning. Journal of Computational Optimization and Reasoning, 4(1), 25–39. https://doi.org/10.12345/jcor.2025.626841
Ali, F., & Hussain, M. (2025). Plant disease detection using deep learning techniques. IECE Journal of Image Analysis and Processing, 1(1), 15–28. https://doi.org/10.5678/jiap.2025.227089
Rahman, M., & Sultana, R. (2024). Plant disease detection and classification using deep learning methods: A comparison study. Journal of Informatics and Web Engineering, 5(2), 55–68. https://doi.org/10.24191/jiwe.v5i2.807
Akter, S., & Lee, J. (2024). An enhanced deep learning model for effective crop pest and disease detection. Journal of Imaging, 10(11), 279. https://doi.org/10.3390/jimaging10110279
Goyal, S., & Bagga, M. (2024). AgriScan: Next.js powered cross-platform solution for automated plant disease diagnosis and crop health management. Journal of Electrical Systems and Information Technology, 11, 45. https://doi.org/10.1186/s43067-024-00169-7
Wei, T., Zhou, Q., & Chen, H. (2024). Benchmarking in-the-wild multimodal plant disease recognition and a versatile baseline (PlantWild dataset). In Proceedings of the ACM International Conference on Multimedia (pp. 1–10). ACM. https://tqwei05.github.io/PlantWild
Roboflow. (2024). Plant disease detection (v19) [Data set]. Roboflow Universe. https://universe.roboflow.com/plant-disease-qn8xm/plant-disease-detection-4htzn/dataset/19
Sharma, A., & Verma, K. (2025). An integrated IoT-based system for automated plant disease detection and management. International Journal of Innovative Science and Research Technology, 10(8), 210–220. https://www.ijisrt.com/an-integrated-iotbased-system-for-automated-plant-disease-detection-and-management
Das, P., & Saha, S. (2023). Machine learning techniques for plant disease detection: An evaluation with a customized dataset [Data set]. Mendeley Data. https://doi.org/10.17632/gpps8gp6m2.1
Bhuyan, M., Rahman, S., & Hassan, M. (2025). A review on automated plant disease detection: Motivation, limitations, challenges, and recent advancements for future research. Journal of King Saud University – Computer and Information Sciences, 37(5), 1–18. https://doi.org/10.1007/s44443-025-00040-3
Biswas, S., Roy, A., & Mandal, S. (2024). A systematic review of deep learning techniques for plant diseases. Artificial Intelligence Review, 57(2), 345–367. https://doi.org/10.1007/s10462-024-10944-7
Li, K., Zhang, M., & Zhou, Y. (2023). An advanced deep learning models-based plant disease detection: A review of recent research. Frontiers in Plant Science, 14, 1158933. https://doi.org/10.3389/fpls.2023.1158933
Kaur, N., & Mehta, R. (2024). Revolutionizing crop disease detection with computational deep learning: A comprehensive review. Environmental Monitoring and Assessment, 196(302), 1–22. https://doi.org/10.1007/s10661-024-12454-z
Singh, V., & Chatterjee, D. (2024). Smart plant disease management: Integrating deep learning and IoT for rapid diagnosis and precision treatment. International Journal of Intelligent Systems and Applications in Engineering, 12(3), 211–219. https://doi.org/10.18280/ijisae.120321
Khan, W., Haroon, M., Khan, A. N., Hasan, M. K., Khan, A., Mokhtar, U. A., & Islam, S. (2022). Dvaegmm: dual variational autoencoder with gaussian mixture model for anomaly detection on attributed networks. IEEE Access, 10, 91160-91176.
Zhou, H., & Chen, X. (2025). PlantCareNet: An advanced system to recognize plant diseases with dual-mode recommendations for prevention. Plant Methods, 21(1), 13. https://doi.org/10.1186/s13007-025-01366-9
Feng, Y., & Lee, H. (2024). On the application of image augmentation for plant disease detection: A systematic literature review. Smart Agricultural Technology, 9, 100590. https://doi.org/10.1016/j.atech.2024.100590
Wang, L., & Zhao, P. (2024). Hierarchical object detection and recognition framework for practical plant disease diagnosis. arXiv preprint. https://arxiv.org/abs/2407.17906
Khan, W., & Haroon, M. (2022). An efficient framework for anomaly detection in attributed social networks. International Journal of Information Technology, 14(6), 3069-3076.
Iqbal, M., & Rafiq, M. (2024). Multi-class plant leaf disease detection: A CNN-based approach with mobile app integration. arXiv preprint. https://arxiv.org/abs/2408.15289