Recent Papers

Maize commonly referred to as corn, is a vital crop that significantly contributes to food security and economic stability, especially in developing nations. It serves as both a dietary staple and an income source for millions worldwide. However, maize production is highly susceptible to various diseases, including Gray Leaf Spot, Common Rust, Northern Leaf Blight, Maize Lethal Necrosis, and Fusarium Ear Rot. These diseases can cause severe financial losses, food shortages, and increased poverty, threatening the livelihoods of communities reliant on maize farming. Accurate and timely detection of these diseases is essential to mitigate these impacts and ensure a stable food supply.Traditional approaches to identifying maize diseases, such as manual crop inspections, are time-consuming, labor-intensive, and often inaccurate. In recent years, machine learning techniques, particularly Convolutional Neural Networks (CNNs), have been utilized to automate this process. While CNNs have shown promise, they face challenges with large datasets and often struggle to capture global context in complex image data, limiting their scalability and accuracy.This paper presents Vision Transformers (ViTs) as an advanced solution for maize disease detection. By utilizing self-attention mechanisms, ViTs can analyze the global structure of images, providing a deeper understanding of visual data compared to CNNs. The aim of this study is to improve the accuracy and efficiency of disease diagnosis using ViTs, equipping farmers with timely information to reduce crop losses. This innovative approach has the potential to revolutionize maize disease management, boost agricultural productivity, and strengthen food security and economic stability in vulnerable regions.

Copyright © 2024 KUTCHERLAPATI VENKATA ABHISHEK VARMA. This is an open access article distributed under the Creative Commons Attribution License.