PDF

Automated Detection and Classification of Tomato Leaf Diseases Using Convolutional Neural Networks

Mohammed Hashim Younis

2025entomato diseasesleaf detectiondeep learningconvolutional neural networksimage classificationprecision agriculture

Abstract

Language:

Tomato (Solanum lycopersicum) production is severely constrained by foliar diseases such as Early Blight, Late Blight, and Septoria Leaf Spot, making early and accurate diagnosis essential for effective crop management. This study proposes a deep learning approach based on Convolutional Neural Networks (CNNs) for automated detection and classification of multiple tomato leaf diseases from images. Using the PlantVillage dataset, which includes over 10 classes of healthy and diseased tomato leaf images, the work applies preprocessing and data augmentation to improve robustness under realistic field-like conditions. The proposed CNN model attains 97.30% classification accuracy on the test set, surpassing traditional machine learning methods and maintaining performance across varied image conditions. Model evaluation using precision, recall, F1-score, and confusion matrices demonstrates strong capability in distinguishing visually similar diseases. The solution is designed to be scalable and low-cost, with potential deployment in mobile applications and precision agriculture systems to support timely, field-level disease management.

Download

Cite This Work

@article{131a7e8e-f9b5-4e65-aad6-2beb8c34eb28,
  title={Automated Detection and Classification of Tomato Leaf Diseases Using  Convolutional Neural Networks  },
  author={Mohammed Hashim Younis},
  year={2025},
  language={en}
}
TY  - JOUR
TI  - Automated Detection and Classification of Tomato Leaf Diseases Using  Convolutional Neural Networks  
AU  - Mohammed Hashim Younis
PY  - 2025
LA  - en
ER  -

Similar Items

Effect of Roasting Temperature for Copper Leaching of Sulfide Concentrate by Combined Methods

Introduction Concerns over air pollution and the environmental problem of acid rain have made governments all over the world tighten their regulations

2023enPDF

Equation Driven Design and Validation of a Reverberatory Furnace for Non ferrous Metals

Roger Rumbu check

2025enPDF$30.00

Extraction of copper and the co-leaching behaviour of other metals from waste printed circuit boards using alkaline glycine solutions

Huan Li, Elsayed Oraby, Jacques Eksteen

Waste printed circuit boards (WPCBs) are a complicated and valuable fraction of electric and electronic waste. The recycling of them is critical to av

2025enPDF

Recovery of valuable metals from mining and mineral processing waste

Roger Rumbu

2025enPDF

New hybrid electrolyte for high performance Li-ion batteries

TohoKu University

This article reports the development of a hybrid polymeric solid electrolyte designed to enhance the safety and performance of lithium-ion batteries (

2022enPDF

A solid battery electrolyte with high performance

PNAS Nexus

This article reports the design and characterization of a high-performance, truly solid polymer electrolyte for lithium-based batteries, addressing lo

2023enPDF