IOT-ENABLED DEEP LEARNING FRAMEWORK FOR CROP DISEASE DETECTION USING IMAGE PROCESSING TECHNIQUES

Abstract

In order to provide real-time plant health monitoring in smart agriculture, this study proposes a deep learning-based crop disease diagnostic system that makes use of IoT and image processing. The suggested system uses Internet-connected sensors to gather data on temperature, humidity, and soil moisture. Additionally, it uses camera modules to capture high-resolution images of crop leaves. CNNs, which are sophisticated deep learning models, are used to scan and analyze these images. They automatically recognize and categorize agricultural diseases with accuracy. With this method, farmers may make decisions more quickly, decrease manual inspection, and identify diseases earlier. Experiments show that this technology is more precise, effective, and scalable than existing techniques. It is therefore perfect for large-scale farming. This study encourages prudent agricultural management, minimizes crop loss, and enhances resource utilization.