Tomato Leaf Disease Classification Dataset

Dataset overview:
The dataset consists of 2995 high-resolution tomato leaf images, which are organized into seven different categories that include disease-stricken specimens, healthy leaf specimens, and deficiencies. These images were captured over different agricultural regions of Bangladesh during a time span of March 10 to March 20, 2025, while showing diverse environmental conditions as well as different leaf growth phases with various disease severity levels.
The classifications of the dataset consist of
Bacterial Spot—117 images
Yellow Leaf Curl Virus—234 images
Early Blight—524 images
Healthy—380 images
Late Blight—112 images
Leaf Miner Flies—884 images
Magnesium Deficiency—744 images
Purpose:
The data provides necessary elements to establish automatic disease identification systems on tomato plants through image processing tools alongside machine learning techniques. The system possesses functions that can develop AI models for precise agriculture and educate deep learning systems for implementing sustainable farming methods. The data set allows three fundamental applications, which include supervised learning model design as well as feature extraction analysis and real-time disease detection systems implementation.

搜集汇总

背景与挑战

背景概述

该数据集包含2995张高分辨率番茄叶片图像，涵盖7种健康状态和病害类型（如细菌性斑点病、黄曲叶病毒等），拍摄于孟加拉国不同农业区域。主要用于开发基于AI的精准农业病害识别系统，支持监督学习模型设计和实时病害检测应用。