Comparative Study of Various Optimizers and Transfer Learning Methods of Rice Leaf Disease Detection Using CNN

Rice leaf disease detection is a crucial task in agriculture to ensure the health and productivity of rice crops. Traditional methods of disease identification are time-consuming and often rely on manual expertise, leading to delays in detection and treatment. This project aims to address this issue by proposing a CNN-based approach for the detection and classification of three common rice leaf diseases: Bacterial Leaf Blight, Brown Spot, and Leaf Smut. From the results, it is observed that the proposed CNN model outperformed the other variants of CNN with an accuracy of 87% and a loss of 0.75 without using dropout and batch normalization.