Guava Leaf Disease Analysis Dataset (GLDAD)

The Guava Leaf Disease Analysis Dataset (GLDAD) is a collection of images designed for the analysis of leaf diseases in guava plants. This dataset includes images of guava leaves that have been categorized into different disease types, as well as healthy leaves. Each image is represented in RGB format and varies in size and quality. This dataset is primarily aimed at research on plant disease detection and classification using image processing and machine learning techniques.

Dataset Details:
Folders:

The dataset is organized into 6 main folders, each representing a different condition of the guava leaves:
Anthracnose: Leaves affected by anthracnose disease.
Healthy: Healthy, unaffected leaves.
Insect Bite: Leaves showing damage from insect bites.
Multiple: Leaves with multiple types of diseases or issues.
Scorch: Leaves exhibiting scorch marks from environmental stress or disease.
YLD (Yellowing): Leaves showing yellowing symptoms due to various factors, like nutrient deficiency or disease.
Total Number of Images:

Each category contains approximately 11,000 images, making the total number of images in the dataset around 66,000 images.
Image Specifications:

Dimensions: The majority of the images are of size 256x256 pixels, though some images have been transformed to other sizes (e.g., 200x200 pixels).
File Format: JPEG format, stored in RGB color mode.
Image Transformations: Each image has undergone multiple transformations, such as rotation, cropping, scaling, flipping, adding noise, etc., to augment the dataset and improve the robustness of machine learning models.
File Size: Varies from around 3 KB to 10 KB per image, depending on transformations applied.
Additional Metadata:

Images were captured on January 11, 2025.
The dataset includes both original images and their transformed counterparts (e.g., transformed_1.jpg, transformed_2.jpg, etc.).
Each image’s metadata includes the creation and modification timestamps, though DPI and compression are not available.
Creation Time: Sat Jan 11 13:45:28 2025
More Raw data : Shuvo Kumar Basak. (2025). Guava Leaf Disease Dataset (GLDD) [Data set]. Kaggle. https://doi.org/10.34740/KAGGLE/DS/6462671
Note for Researchers Using the Guava Leaf Disease Analysis Dataset (GLDAD):

This dataset, titled Guava Leaf Disease Analysis Dataset (GLDAD), was created by Shuvo Kumar Basak. If you use this dataset for your research or academic purposes, please ensure to cite this dataset appropriately. If you have published your research using this dataset, please share a link to your paper. Good Luck.

番石榴叶病害分析数据集（Guava Leaf Disease Analysis Dataset，简称GLDAD）是专为番石榴植株叶部病害分析构建的图像数据集。本数据集涵盖按不同病害类型分类的番石榴叶图像，同时包含健康番石榴叶图像。所有图像均采用RGB色彩格式，尺寸与画质存在差异。本数据集主要面向基于图像处理与机器学习技术的植物病害检测与分类研究。

数据集详情：
文件夹结构：
本数据集共分为6个主文件夹，每个文件夹对应番石榴叶的一种状态：
- 炭疽病（Anthracnose）：受炭疽病侵害的番石榴叶
- 健康叶片：未受任何病害侵扰的健康番石榴叶
- 虫咬损伤：存在虫咬痕迹的番石榴叶
- 复合病害：同时存在多种病害或损伤的番石榴叶
- 焦枯病：因环境胁迫或病害出现焦枯痕迹的番石榴叶
- 黄化症（Yellowing，简称YLD）：因营养缺乏或病害等多种因素出现黄化症状的番石榴叶

图像总规模：
每个分类约包含11000张图像，数据集总图像量约为66000张。

图像规格：
- 图像尺寸：绝大多数图像尺寸为256×256像素，部分图像经转换后采用其他尺寸（如200×200像素）
- 文件格式：采用JPEG格式，存储为RGB色彩模式
- 图像增强处理：为扩充数据集并提升机器学习模型的鲁棒性，所有图像均经过多种变换处理，包括旋转、裁剪、缩放、翻转、添加噪声等
- 文件大小：单张图像文件大小约为3KB至10KB，具体取决于所应用的变换操作

附加元数据：
- 图像采集时间：2025年1月11日
- 数据集同时包含原始图像与经过变换的增强图像（例如transformed_1.jpg、transformed_2.jpg等）
- 每张图像的元数据均包含创建与修改时间戳，但未提供DPI与压缩相关信息
- 采集时间：2025年1月11日 星期六 13:45:28

原始数据集来源：Shuvo Kumar Basak. (2025). 番石榴叶病害数据集（Guava Leaf Disease Dataset，简称GLDD）[数据集]. Kaggle. https://doi.org/10.34740/KAGGLE/DS/6462671

番石榴叶病害分析数据集（GLDAD）使用说明：
本数据集由Shuvo Kumar Basak构建，名称为番石榴叶病害分析数据集（GLDAD）。若您将本数据集用于研究或学术用途，请务必对该数据集进行恰当引用。若您基于本数据集发表了研究成果，请分享您的论文链接。祝研究顺利。