Comparative Analysis of Machine Learning Algorithms for Crop Disease Detection Using Leaf Image Data
Dr. Anoop Kumar Sharma & Dr. James Osei
Published in IJMEER (Vol. 1, Issue 2, April–June 2026) · Pages 123-134 · DOI: 10.5281/zenodo.21809155
Abstract
Timely and accurate detection of crop diseases is critical for minimising agricultural yield losses and reducing the overuse of chemical pesticides. This study conducted a comparative performance evaluation of three machine learning approaches — Convolutional Neural Network (CNN), Support Vector Machine (SVM), and Random Forest (RF) — for the automatic detection and classification of nine common crop diseases across four crop species using leaf image data drawn from the PlantVillage dataset (54,306 images). The fine-tuned CNN architecture achieved the highest overall classification accuracy of 94.2%, outperforming SVM (87.1%) and RF (82.3%).
Keywords
Author Affiliations
- Assistant Professor, Department of Computer Science, Government Degree College, Rampur, Uttar Pradesh
- Lecturer, Department of Computer Science, University of Ghana, Legon, Accra, Ghana
How to Cite
Copyright & Licensing
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
You may share, copy, and redistribute this work for non-commercial purposes, provided you give appropriate credit to the author(s) and IJMEER. Commercial use is not permitted.