Crop Disease Detection using Computer Vision

Abstract

The rapid growth of global agriculture faces a pressing challenge in the form of crop diseases, threatening food security. This research delves into the domain of machine learning and deep learning models, utilizing leaf images for crop disease detection. It encompasses the role of Information and Communication Technology (ICT) tools in the agricultural land-scape's modernization, in-depth exploration of prevalent crop diseases along with the drawbacks of conventional identification techniques. The research also includes an extensive literature review that underscores the burgeoning importance of ML and DL models in automating disease identification. Dataset analysis underscores the significance of meticulously curated datasets for model training and validation. The core of this study lies in the comparative evaluation of ML and DL models, assessing their potential to revolutionize agricultural practices. Acknowledging inherent limitations and challenges, such as dataset availability and model generalization, this study navigates the intersection of technology and agriculture, offering promising tools for crop disease detection.