Leaf Disease Detection and Severity using Support Vector Machine

P. Divya¹, P. Jahnavi², G. Sai lohith³, L. Sampath kumar⁴
Supervisor: Mr. N YELLAJI RAO M. Tech (Ph.D), Assistant Professor, Dept. of CSD, VIET
¹Department of CSE (DS), Visakha Institute of Engineering and Technology, Andhra Pradesh, India
2Department of CSE (DS), Visakha Institute of Engineering and Technology, Andhra Pradesh, India
3Department of CSE (DS), Visakha Institute of Engineering and Technology, Andhra Pradesh, India
4Department of CSE (DS), Visakha Institute of Engineering and Technology, Andhra Pradesh, India

Abstract - This paper presents a Leaf Disease Detection and Severity Analysis System designed to improve crop health monitoring through intelligent image processingand automated classification techniques. The system  analyses leaf images in real time and identifies diseasepatterns using machine learning methods such as Support Vector Machine (SVM). Based on this analysis, leaves are classified into healthy and diseased categories, and specific disease types are detected using extracted features like color, texture, and shape. A threshold-ased decision mechanism is applied to estimate disease severity by calculating the proportion of affected leaf area and categorizing theinfection level accordingly. Unliketraditional agricultural practices that rely on manual  inspection, the proposed system ensures consistentandaccurate detection through automation. The system is implemented using a user-friendly interface integrated with backend processing modules and locally executedmachine learning models to ensure efficiency and  reliability. Experimental results demonstrate a significantimprovement in disease detection accuracy and effective severity estimation. The proposed approach provides a scalable and adaptive solution for enhancing cropmanagement among farmers and agricultural professionals