Paddy Care: Paddy Disease Identification and Classification Using Deep DenseNet Network

Half of the world's population depends on rice as a staple crop, but disease threats to it are significant, particularly in major exporting nations like India. The delayed and inefficient nature of manual detection techniques worsens environmental issues brought on by excessive pesticide use. Beyond traditional approaches, recent deep learning innovations such as CNNs, In-ception V3 and MobileNetV2 show promise in disease diagnosis. Compared with existing methods, our proposed Deep DenseNet Network (DNN) achieves an astonishing 99.94 % accuracy in diag-nosing rice diseases. To have a greater agricultural impact, future research will concentrate on improving computing efficiency and expanding disease detection capabilities. Future research should focus on enhancing disease detection and computational efficiency for sustainable agricultural systems through deep learning and advanced image classification.