Dataset for Detecting Anthracnose in Hog Plum and Bottle Gourd Leaves.

Tittle: Agricultural Disease Management: Dataset for Detecting Anthracnose in Hog Plum and Bottle Gourd Leaves.
In this dataset, a total of 4883 leaf samples were collected from two crop species—hog plum (Spondias mombin) and bottle gourd (Lagenaria siceraria)—sourced from various locations in Bangladesh, including agricultural fields, grocery stores, and other sources. The leaves were carefully documented and categorized into healthy and diseased groups to create a comprehensive dataset for accurate classification of anthracnose. The distribution of leaf samples is as follows:
Bottle Gourd: 15603 samples
Original: 3323 samples
Healthy Leaves: 915 samples
Diseased Leaves: 1720 samples
Extreme Diseased Leaves: 688 samples
Augmented: 12280 samples
Healthy Leaves: 3659 samples
Diseased Leaves: 5718 samples
Extreme Diseased Leaves: 2903 samples

Collection Sites: 1,833 samples from Ashulia Model Town, Ashulia, Dhaka, Bangladesh, and 1,500 from Baroghoria, Chapai Nawabganj, Rajshahi, Bangladesh.

Hog Plum: 8302 samples
Original: 1560 samples
Healthy Leaves: 545 samples
Diseased Leaves: 798 samples
Torn Diseased Leaves: 217 samples
Augmented: 6742 samples
Healthy Leaves: 2397 samples
Diseased Leaves: 3313 samples
Torn Diseased Leaves: 1032 samples

Collection Site: Ashulia Model Town, Ashulia, Dhaka, Bangladesh.

Purpose
The Dataset of Anthracnose in Hog Plum and Bottle Gourd Leaves serves a critical role in deep learning applications, particularly in image classification for automatic disease detection. It can be used to train models like Convolutional Neural Networks (CNNs) to identify and classify anthracnose based on visual features such as leaf shape, color, and texture. This dataset is useful in areas like agricultural supply chain automation, real-time disease identification in farming settings, and crop quality control. Additionally, it can be integrated with environmental data (e.g., temperature, humidity, rainfall) to enhance predictive models that forecast disease risks under varying climatic conditions. Ultimately, this dataset helps advance machine learning models for automated disease detection, crop health monitoring, and agricultural productivity improvements, making a significant impact on the agriculture industry and beyond.

标题：农业病害管理：检测猪李和瓜叶黑斑病的 dataset。本 dataset 共收集了 4883 份叶片样本，涉及两种作物品种——猪李（Spondias mombin）和瓜类（Lagenaria siceraria），样本来源包括孟加拉国的农业田地、杂货店以及其他途径。叶片样本经过细致的记录和分类，分为健康与病害两组，以构建一个全面的数据集，以实现黑斑病的精确分类。叶片样本的分布情况如下：瓜类：15,603 样本，其中原始样本 3,323 份，健康叶片 915 份，病害叶片 1,720 份，极度病害叶片 688 份；增强样本 12,280 份，其中健康叶片 3,659 份，病害叶片 5,718 份，极度病害叶片 2,903 份。收集地点：孟加拉国达卡市阿舒利亚模范镇 1,833 样本，以及拉杰沙希地区查派纳瓦布甘杰的巴罗戈里亚 1,500 样本。猪李：8,302 样本，其中原始样本 1,560 份，健康叶片 545 份，病害叶片 798 份，撕裂病害叶片 217 份；增强样本 6,742 份，其中健康叶片 2,397 份，病害叶片 3,313 份，撕裂病害叶片 1,032 份。收集地点：孟加拉国达卡市阿舒利亚模范镇。目的：猪李和瓜叶黑斑病 dataset 在深度学习应用中扮演着至关重要的角色，特别是在图像分类领域的自动病害检测。该 dataset 可用于训练卷积神经网络（CNN）等模型，基于叶片的形状、颜色和纹理等视觉特征来识别和分类黑斑病。该 dataset 在农业供应链自动化、田间环境中的实时病害识别以及作物质量控制等领域具有实际应用价值。此外，它还可以与环境数据（例如温度、湿度、降雨量）相结合，以增强在不同气候条件下预测疾病风险的预测模型。最终，本 dataset 有助于推进机器学习模型在自动病害检测、作物健康监测以及农业生产力提升方面的应用，对农业行业乃至更广泛的领域产生深远影响。