Rice is one of the most important staple crops in the world and a major source of food for millions of people. However, rice plants are susceptible to various diseases that can cause significant losses in yield and quality. Among these diseases, leaf blast, bacterial blight, and brown spot are the major attacking diseases that can cause devastating damage to rice crops.
To address this issue, the development of an efficient and accurate automated disease detection system is crucial. In this project, we aim to develop a machine learning model that can accurately classify the three major attacking diseases of rice plants based on leaf images.
By using advanced machine learning techniques, our model will be able to provide fast and accurate detection of diseases, enabling farmers to take prompt and effective measures to control the spread of the diseases and minimize crop losses.
This project has the potential to revolutionize rice crop management and contribute to the sustainable development of agriculture.
Based on the provided data, it appears that the Xception model trained on augmented data has the highest validation accuracy among the five models evaluated, with a validation accuracy of 0.9667. Additionally, the Xception model has a relatively low validation loss, indicating that it is effectively minimizing the difference between predicted and actual labels.
Overall, the Xception model appears to have the best balance of accuracy and efficiency among the models evaluated, which is why we will select it as the final model.