ML Based Apple Leaf Disease Detection

This research paper delves into the evaluation of various machine learning algorithms for the detection of diseases in apple leaves. Models such as VGG, DenseNet, ResNet, EfficientNet, ConvNextBase, and Vision Transformer (ViT) were scrutinized in this study. The assessment involved gauging the efficacy of each model in identifying and categorizing diseases using a dataset comprised of high-resolution images of apple leaves exhibiting various ailments. The findings revealed that these models excel in distinguishing between healthy and diseased leaves, albeit with differences in their ability to pinpoint specific diseases. This investigation contributes to the field of precision agriculture by automating disease detection, thereby aiding in the early detection and treatment of diseases to bolster fruit yield in apple orchards.