Abstract :

The Increasing Prevalence Of Plant Diseases Poses A Critical Threat To Global Agricultural Productivity, Necessitating Rapid And Reliable Diagnostic Solutions. This Study Presents An Intelligent, Automated System For Plant Disease Detection And Severity Estimation, Integrating Deep Learning And Computer Vision. A Lightweight Convolutional Neural Network (CNN) Based On The MobileNetV2 Architecture Was Trained On The PlantVillage Dataset Comprising 43,444 Images Across 38 Disease Classes, Achieving 98.02% Training And 97.82% Validation Accuracy. To Quantify Disease Severity, An Image Processing Pipeline Employing HSV Transformation, Thresholding, And Contour Detection Was Implemented To Segment Infected Regions And Compute The Percentage Of Affected Leaf Area. The System Delivers Both Disease Classification And Severity Analysis, Providing Actionable Insights For Precision Agriculture. Its Scalability And Real-time Potential Mark A Significant Step Toward Sustainable Crop Management And Intelligent Plant Health Monitoring. Keywords—Plant Disease Identification; Deep Learning; MobileNetV2;Convolution Nueral Network; Image Processing; Severity Estimation; Precision Agriculture; Computer Vision; PlantVillage Dataset; Contour Detection; HSV Color Space; Automated Diagnosis

Published:

26-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

467-474

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite