Advancements in Agricultural Technology: Vision Transformer-Based Potato Leaf Disease Classification

Abstract

Potato (Solanum tuberosum) is an essential global food crop that is susceptible to various leaf diseases, which can drastically reduce agricultural productivity. Accurate and timely detection of these diseases is crucial for effective management and ensuring food security. This research investigates the application of Vision Transformer (ViT) models, particularly the ViT_B_16 architecture, for detecting and classifying potato leaf diseases such as early blight, late blight, and healthy leaves. Utilizing a comprehensive dataset from Kaggle, which includes 2,152 images across three categories, along with an additional custom dataset, the ViT model is fine-tuned and evaluated using separate training, testing, and validation sets. The findings reveal an impressive accuracy of 99.55%, underscoring the efficacy of ViT-based methods for precise and dependable detection of potato leaf diseases. This study enhances agricultural technological practices by providing a robust tool for early disease diagnosis and strategic agricultural planning.