Early Detection of Tomato Leaf Diseases Using Hybrid Machine Learning Techniques

Download
Download is available until
  • Version
  • Download 17
  • File Size 1.36 MB
  • File Count 1
  • Create Date 17 June, 2025
  • Last Updated 18 June, 2025

Author: Rita Vora , Sanjay Pandey, Ravindra Duche

DOI : 10.46335/IJIES.2025.10.8.1

Abstract – Disease detection in tomato leaves is a critical aspect of ensuring healthy plants and maximizing agricultural productivity. In this research work, we are doing a hybrid machine learning-based analysis for true identification of healthy and diseased leaves of tomato plants. It achieves an accuracy of 92.5% with a precision of 91.8% and recall of 93.2%, indicating its efficacy to restrict false positives and false negatives. Thus, it can be a useful tool for farmers with an AUC-ROC score of 0.97. The findings underscore its ability to mitigate crop loss and improve disease management strategies. Future work will focus on improving disease detection, building the model's database, and incorporating the model into several real-time monitoring systems for a wide range of farming applications.

Received on: 09 May,2025   Revised on: 15 June,2025     Published on: 17 June,2025