Apple Leaf Diseases Image Dataset of ICAR-CITH

This dataset, titled Apple Leaf Diseases Image Dataset of CITH, contains high-quality images of apple leaves affected by four major diseases: Alternaria leaf blotch, Apple scab, Powdery mildew, and Mosaic virus. • Alternaria leaf blotch, Powdery mildew, and Mosaic virus images were collected from the experimental fields of the ICAR–Central Institute of Temperate Horticulture (CITH), Srinagar, India under natural field conditions. • Apple scab images were sourced from publicly available data on the Kaggle platform to complement field-collected data. The dataset is intended to support research in plant disease diagnosis, computer vision, and precision horticulture, particularly in the development and evaluation of machine learning and deep learning models for disease classification and detection in apple crops. Each image is provided in its original resolution without preprocessing, allowing flexibility for various experimental setups. All images are categorized by disease type and stored in separate folders for easy accessibility. Potential Applications: • Automated apple leaf disease detection and classification • Deep learning model training and benchmarking • Comparative studies on disease detection under varying background conditions • Educational and extension activities in horticulture plant pathology Researchers and practitioners are encouraged to cite this dataset when used in publications or projects.本数据集命名为CITH苹果叶部病害图像数据集（Apple Leaf Diseases Image Dataset of CITH），包含四类主流苹果叶部病害的高清图像：苹果链格孢叶斑病（Alternaria leaf blotch）、苹果黑星病（Apple scab）、苹果白粉病（Powdery mildew）及苹果花叶病毒病（Mosaic virus）。 • 苹果链格孢叶斑病、苹果白粉病及苹果花叶病毒病的图像采集自印度斯利那加的印度农业研究理事会-温带园艺中央研究所（ICAR–Central Institute of Temperate Horticulture，缩写CITH）的试验田，所有样本均于自然田间条件下拍摄获取。 • 苹果黑星病的图像取自Kaggle平台的公开数据集，以补充田间采集的样本数据。 本数据集旨在为植物病害诊断、计算机视觉及精准园艺领域的研究提供支撑，尤其可用于开发、评估用于苹果作物病害分类与检测的机器学习与深度学习模型。 所有图像均保留原始分辨率且未经过预处理，可为各类实验设置提供灵活适配空间。所有图像按病害类型分类并存储于独立文件夹中，便于快速访问与调用。 潜在应用场景： • 自动化苹果叶部病害检测与分类 • 深度学习模型训练与基准测试 • 不同背景条件下病害检测的对比研究 • 园艺植物病理学领域的教学与推广活动 呼吁所有使用本数据集的研究人员与从业者，在发表学术成果或开展相关项目时对本数据集予以引用。