DESIGN AND IMPLEMENTATION OF RICE LEAF DISEASE PREDICTION USING EXPERT SYSTEM

Rice is a staple food crucial to global food security, yet its production is severely threatened by diseases that cause significant yield and quality losses, particularly in developing nations like Nigeria. Traditional methods of disease detection, which rely on manual visual inspection by farmers or experts, are often slow, subjective, and prone to error, leading to delayed treatment and economic damage. The need for a rapid, accurate, and accessible solution is paramount. This project addresses this challenge by designing and implementing a web-based expert system for the automated detection of rice leaf diseases. The system leverages the power of Convolutional Neural Networks (CNN), a deep learning technique, to analyze images of rice leaves and identify common diseases such as Bacterial Leaf Blight, Brown Spot, and Leaf Blast. The methodology encompassed data collection from both public repositories and field visits in Kano State, Nigeria, followed by extensive image preprocessing and the development of a robust CNN model for classification. A key feature of the developed system is its deployment as a web application, ensuring accessibility to farmers using standard smartphone browsers without the need for specialized hardware. The system was designed with an offline-first architecture, utilizing TensorFlow Lite to provide reliable disease predictions even in areas with poor internet connectivity. The application features a user-friendly interface with visual and color-coded outputs to cater to farmers with varying levels of literacy. The system underwent rigorous testing, confirming its functional performance, usability, and compatibility. The implemented CNN model achieved a high level of accuracy in classifying the targeted diseases. The study concludes that this web-based, AI-driven solution provides a practical, cost-effective, and scalable tool for early detection of rice leaf diseases. It empowers farmers to take timely action, thereby reducing crop losses, minimizing unnecessary pesticide use, and contributing to enhanced food security and sustainable agricultural practices in Nigeria and similar regions.