Efficient Banana Leaf Disease Classification Using Vision Transformer (ViT) Model

Diseases and bugs present a significant danger to agricultural chain production due to their ability to affect both the quality and quantity of the end product. The expeditious evaluation of these maladies facilitates enhanced productivity through the augmentation of agricultural output and the stimulation of economic expansion. As a result of the increased demand for disease monitoring systems, artificial intelligence has been implemented. The dataset utilized in the proposed study was curated from Kaggle and comprised RGB images depicting maladies affecting plantain leaves. Banana plant ailments were identified utilizing a ViT model. The performance of this model, which has been executed with an assortment of epochs, has been evaluated concerning both loss and accuracy. The maximum accuracy of 96.88% was attained during epoch 100.