Rice Leaf Diseases Classification Using Discriminative Fine Tuning and CLR on EfficientNet

Rice cultivation in Nepal is effect by many factors, one of the main factor rice leaf diseases which limits crops production. Image classification classify different diseases. dataset taken from open source platform. Pre-processing image done followed feature extraction and images. This thesis presents into four classes, namely: Brown Spot, Healthy, Hispa, Leaf Blast using Convolutional Neural Network (CNN) architecture EfficicentNet-B0 EfficicentNet-B3 based on fine-tuning with cyclical learning rate discriminative fine-tuning. It found that test accuracy EfficientNet-B0 81.96% EfficientNet-B3 85.12% EfficienNet-B0 83.99% 89.18% for 15 epochs. The results also conclude CNN architectures work better than rate. models are evaluated recall, precision F1-score metrics.