This study investigates the use of deep learning models, Visual Geometry Group 16 (VGG16), AlexNet and a custom convolutional neural network (CNN), for classifying potato leaf images into categories of early blight, late blight and healthy leaves. The dataset, comprising 3293 images, combining locally sourced images from Anand Agricultural University (AAU), Gujarat, India, and images from the PlantVillage (PV) repository. Various configurations were tested, including batch size of 32 and 64 and training epochs of 30 and 60. Results indicate that the custom CNN achieved the highest performance, with an accuracy of 98.8% and minimum loss of 0.055, surpassing both VGG16 and AlexNet. Notably, the custom CNN required only 128,387 trainable parameters, significantly fewer than VGG16 (138 million) and AlexNet (58 million), highlighting its efficiency. This efficiency demonstrates the custom CNN’s optimized architecture, enabling high classification performance with lower computational demands.
Full publication URL
