Crop Health Monitoring Dataset: Disease Classification in Maize, Tea, Tomatoes, Apples, and Beans

The Multi-Crop Disease Classification Dataset provides a diverse collection of plant health data across five critical crops: maize, tea, tomatoes, apples, and beans. It serves as a valuable resource for developing and evaluating machine learning models aimed at accurately classifying common diseases affecting these crops, alongside a category representing healthy plants.

Key Features:

The dataset meticulously documents and labels two prevalent diseases for each crop, alongside a category representing healthy plants. To ensure inclusivity, a range of diseases commonly observed in agricultural settings is represented, offering a comprehensive perspective on plant health challenges. Efforts have been made to maintain a balanced distribution of samples across disease classes and crops to enhance model training efficacy and generalization.

Captured using low-cost cameras, the dataset includes images showcasing various stages of disease progression, particularly for crops where visual symptoms are indicative of disease presence. These images are complemented by textual descriptions detailing observable symptoms, enriching the dataset with both visual and textual analysis capabilities. Each data instance is labeled with the corresponding crop type, disease class, and health status, facilitating supervised learning tasks such as disease classification and health monitoring.

Potential Applications:

The dataset is well-suited for training and evaluating classification models, including convolutional neural networks (CNNs), decision trees, and support vector machines (SVMs), for automated disease diagnosis and plant health monitoring. Furthermore, it enables the development of intelligent agricultural systems capable of early disease detection, targeted intervention, and optimized crop management practices. Researchers, academia, and agricultural professionals can utilize the dataset to study disease patterns, devise mitigation strategies, and enhance agricultural productivity and sustainability.