Corn Leaf Disease Classification Dataset

Published: 6 April 2026| Version 1 | DOI: 10.17632/hmkd6nbngr.1
Contributor:
Md Shajedur Rahman Daffodil International University

Description

This dataset contains approximately 17,000 labeled images of corn (maize) leaves, collected for research purposes in plant disease detection and classification. The dataset is organized into five distinct classes: Common Rust, Corn Leaf Blight, Gray Leaf Spot, Healthy, and Insect Damage. Each image represents real-world field conditions, capturing variations in lighting, background, and disease severity. This diversity makes the dataset suitable for training and evaluating machine learning and deep learning models for agricultural disease diagnosis. The dataset is well-structured and can be used for image classification tasks, particularly in computer vision applications related to precision agriculture. It is intended to support research, model development, and performance benchmarking in crop disease detection systems.

Files

Steps to reproduce

This dataset was created by collecting corn leaf images from various sources, including field observations and publicly available image repositories. The images were manually reviewed and categorized into five classes: Common Rust, Corn Leaf Blight, Gray Leaf Spot, Healthy, and Insect Damage. All images were organized into separate folders based on their respective class labels. Basic preprocessing steps were applied, including image resizing and format standardization to ensure consistency across the dataset. To reproduce this dataset, similar corn leaf images can be collected under different environmental conditions. The images should then be manually labeled according to disease type and organized into class-specific directories. Standard preprocessing techniques such as resizing, normalization, and data cleaning can be applied before using the dataset for machine learning or deep learning tasks.

Categories

Corn Entomology

Licence