A Comparative Analysis of Machine Learning Classifiers for Fruit Disease Detection

DOI

https://www.doi.org/10.59256/ijire.20260703033

Published In

Volume 7, Issue 3 (2026)

Published Online

May-June 2026

Pages

313-326

Article Type

Original Article

Check for updates

Precise fruit disease identification and classification are vital for minimizing economic losses, ensuring food security, and maintaining high quality produce. India faces significant fruit losses, ranging from 6% to 15%, resulting in economic damage exceeding ₹1.5 lakh crore annually [1, 2]. This challenge is mirrored globally, with estimates suggesting losses for fruits and vegetables reaching as high as 50% [2]. To address this challenge and safeguard crop health, Artificial Intelligence (AI) offers a promising solution. This study explores the effectiveness of machine learning, a subfield of AI that allows computers to learn from data without explicit programming. We investigate five prominent machine learning algorithms - Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors and Gaussian Naive Bayes (GNB) - in classifying fruit diseases using a plant village dataset. By evaluating performance metrics like accuracy, precision, and recall, this research aims to identify suitable classifiers for automated disease detection and contribute to robust agricultural disease management strategies. This, in turn, empowers farmers with tools for proactive disease control, fostering a sustainable and resilient food system