Deep Learning-Driven Mobile Application for Rice Crop Disease Detection Using CNN

This study presents a deep learning-based mobile app for rice crop disease detection using a MobileNetV2-based CNN model trained on a dataset of 4,700 rice leaf images. The app accurately identifies diseases like Bacterial Leaf Blight, Leaf Smut, and Brown Spot, achieving 96.49% accuracy and outperforming models like SVM and Random Forest while maintaining efficiency for mobile use. The app aims to support Filipino farmers in managing crop diseases, improving farm productivity and food security. Additional features, such as real-time weather updates and a community forum, enhance accessibility. Evaluations through TAM and ISO/IEC 25010 confirm its effectiveness and potential for widespread adoption.