An Improved MobileNet for Disease Detection on Tomato Leaves

Tomatoes are widely grown vegetables, and farmers face challenges in caring for them, particularly regarding plant diseases. The MobileNet architecture is renowned its simplicity compatibility with mobile devices. This study introduces as a deep learning model to enhance disease detection efficiency tomato plants. evaluated on dataset of 2,064 leaf images, encompassing early blight, spot, yellow curl, healthy leaves. Results demonstrate promising accuracy, exceeding 0.980 classification 0.975 distinguishing between diseases cases. Moreover, the proposed outperforms existing approaches terms accuracy training time detection.