Deep learning for detection cassava leaf disease

Abstract

Abstract In this research, an intelligent system for detecting cassava leaf disease has been developed by utilizing the MobileNetV2 deep learning model and displaying it using a python graphical user interface (GUI). There are five disease classes used in this study, namely Cassava Bacterial Blight (CBB), Cassava Brown Steak Disease (CBSD), Cassava Green Mite (CGM), and Cassava Mosaic Disease (CMD) and Healthy. The results showed that the overall accuracy of the test data obtained was 65,6%. The GUI application program was made to be operated efficiently for beginners and can be used by cassava farmers in the field.