Leaf Disease Detection System Using Machine Learning

Abstract

Plant leaf diseases significantly impact agricultural productivity and crop yield. Early detection of these diseases is essential to reduce losses and improve plant health. This research presents an automated leaf disease detection system using image processing and machine learning. A Convolutional Neural Network (CNN) is employed to classify plant leaf images as healthy or diseased. The trained model is integrated into a web-based application developed with Python Flask for easy user interaction. The proposed system provides a fast, accurate, and reliable solution for plant disease identification and supports efficient agricultural management.

Introduction

Plant leaf disease detection is an automated system that identifies whether a plant is healthy or diseased by analyzing leaf images using computer vision and machine learning. Traditional manual inspection methods are time-consuming, labor-intensive, and prone to errors. Automated systems enable early disease detection, which helps prevent crop loss, reduce pesticide use, and improve agricultural productivity, especially in large-scale farms.

The study highlights common leaf disease types caused by viruses, bacteria, and fungi. Viral diseases show symptoms like mosaic patterns, leaf curling, and stunted growth. Bacterial diseases produce water-soaked spots that turn into necrotic lesions. Fungal infections cause spots, blight, and powdery growth, such as Early Blight in tomato and Late Blight in potato. Early recognition of these symptoms is essential for effective disease management.

The proposed system uses a Convolutional Neural Network (CNN) for automatic classification of leaf images as healthy or diseased. The system includes image acquisition, preprocessing (resizing, noise removal, normalization, and segmentation), feature extraction, and classification. CNN automatically learns features such as color, texture, shape, and edges, eliminating the need for manual feature engineering. The model is deployed using a Python Flask web application, allowing users to upload leaf images and receive instant predictions.

Compared to traditional machine learning methods like SVM and KNN, CNN provides higher accuracy, better generalization, and improved robustness under varying conditions. The system is scalable, user-friendly, and supports early disease detection.

However, it depends on high-quality labeled data, requires significant computational resources, and may be affected by environmental factors such as lighting and background noise.

Conclusion

In this research, a CNN-based leaf disease detection system was developed for tomato and potato crops. The system accurately classifies healthy and diseased leaves and is deployed through a web interface using Python Flask, providing a practical tool for farmers. The proposed approach demonstrates high accuracy, scalability, and user-friendliness, making it an effective solution for modern agricultural disease management. Future work can expand the dataset to include more crops and diseases and integrate realtime detection using mobile applications or IoT enabled devices.

References

[1] Arpita Patel, Mrs. Barkha Joshi, “A Survey on the Plant Leaf Disease Detection Techniques,” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), Vol. 6, Issue 1, Jan. 2017. [2] V. Suresh, D. Gopinath, M. Hemavarthini, K. Jayanthan, Mohana Krishnan, “Plant Disease Detection using Image Processing,” International Journal of Engineering Research & Technology (IJERT), Vol. 9, Issue 03, March 2020. [3] Kiran R. Gavhale, Ujwalla Gawande, “An Overview of the Research on Plant Leaves Disease detection using Image Processing Techniques,” Yashwantrao Chavan College of Engineering, Nagpur, India, 2019. [4] Payal Trivedi, Yogendra Narayan, Vinayakumar Ravi, et al., “Plant Leaf Disease Detection and Classification Using Segmentation Encoder Techniques,” The Open Agriculture Journal, 2024. [5] Anuja Bhargava, Aasheesh Shukla, Om Prakash Goswami, Mohammed H. Alsharif, Peerapong Uthansakul, Monthippa Uthansakul, “Plant Leaf Disease Detection, Classification, and Diagnosis Using Computer Vision and Artificial Intelligence: A Review,” IEEE, 2020

Copyright

Copyright © 2026 Ajay Ramesh Shelke, Pravin Santosh Shelke, Sumit Santosh Shelke, Gaurav Navnath Gagare, Minaj Shaikh. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.