DESIGN AND IMPLEMENTATION OF RICE LEAF DISEASE PREDCTION SYSTEM USING MOBILE APP. (A CASE STUDY OF KANO STATE)

Rice is a vital staple crop in Nigeria, particularly in Kano State, where its production significantly contributes to food security and the local economy. However, rice yield is often threatened by various leaf diseases, which are difficult to detect early using traditional methods. This project presents the design and implementation of a mobile-based rice leaf disease prediction system aimed at assisting farmers in the early identification and management of common rice leaf diseases. The system utilizes image processing and machine learning techniques to analyze images of rice leaves captured through a mobile application. The application is designed to classify diseases such as leaf blast, brown spot, and bacterial blight with a high level of accuracy. A user-friendly interface allows farmers and agricultural extension workers to easily upload images and receive instant diagnostic feedback along with recommended treatment options. The methodology involves dataset collection, image preprocessing, feature extraction, and model training using a supervised learning algorithm. The trained model is integrated into a mobile platform to ensure accessibility and real-time usage in rural farming environments. The system was tested using field data from selected rice farms in Kano State, and the results demonstrate improved accuracy in disease detection and faster response time compared to manual identification methods. This project highlights the potential of mobile technology and artificial intelligence in modernizing agriculture, reducing crop losses, and enhancing productivity. It provides a scalable solution that can be adapted to other regions and crops, thereby contributing to sustainable agricultural practices.