Real-Time Oryza Sativa Disease Diagnosis using a Hybrid Deep Learning and Edge Computing Framework

Rice (Oryza sativa L.) is a staple food for billions globally, making its protection against diseases crucial for food security. This paper proposes a novel framework for real-time diagnosis of diseases of leaves of rice through the use of hybrid edge computing and deep learning techniques. The framework uses deep learning to its full potential models for accurate disease classification while utilizing edge computing for efficient on-field deployment and real-time results. Our approach discusses the constraints of traditional techniques by enabling timely disease identification in resource-constrained environments, empowering farmers with immediate decision-making capabilities. We thoroughly evaluate the proposed framework on real-world rice leaf disease datasets, demonstrating its effectiveness and potential to revolutionize rice disease management practices.