Impact of datasets on the effectiveness of MobileNet for beans leaf disease detection

Bean is a widely cultivated crop worldwide; however, it is susceptible to various diseases that can adversely affect the quality of beans, including rust and angular leaf spot diseases. These diseases can cause significant damage by wiping out hectares of crops, emphasizing the need for early detection. Deep learning algorithms have shown remarkable performance in image detection tasks, achieving high accuracy on many datasets. This study used a deep learning technique, specifically the MobileNet architecture, to detect bean leaf disease. We evaluated the effectiveness of the approach by testing the model on three different bean leaf image datasets with varying difficulty. MobileNet was chosen due to its ability to achieve high performance with a reduced number of parameters and faster execution time. Additionally, we examined the impact of the datasets on the model's performance and presented a comparative analysis of the three datasets, and then we applied the GradCAM technique to the model's predictions. Experimental results showed that the proposed approach achieved remarkable accuracy, with over 92% accuracy on all three datasets. The study provides a valuable contribution to the field of plant disease detection and highlights the potential of deep learning techniques in detecting bean leaf disease.