Leaf Disease Detection with Cloud Integration

Abstract

Leaf diseases significantly impact agricultural productivity worldwide. Traditional manual diagnosis is often time-consuming and prone to human error. This paper presents a deep learning-based leaf disease detection system integrated with cloud infrastructure to provide scalable, real-time, and accessible solutions for farmers and researchers. The proposed model leverages Convolutional Neural Networks (CNNs) trained on annotated datasets of diseased and healthy leaves. The system integrates with a Fast API backend and cloud storage for efficient deployment and data access. Evaluation metrics, including accuracy, precision, recall, and F1- score, validate the robustness of the model. Results demonstrate improved disease classification accuracy compared to traditional methods. Cloud-based design ensures scalability, making it suitable for large-scale agricultural applications. This research contributes to smart agriculture by providing a sustainable and reliable disease monitoring solution.