A Deep Dive into Modern Approaches for Plant Disease Detection, with a Focus on Sugarcane

The increasing global demand for agricultural products necessitates efficient plant disease detection methods to safeguard crop yields and food security. This survey paper provides a comprehensive overview of the evolving landscape of plant disease detection using machine learning and deep learning techniques, culminating in a detailed examination of their applications in the context of sugarcane health. A thorough review of state-of-the-art ML algorithms, such as Support Vector Machines, Random Forests, & k-Nearest Neighbors, is presented, showcasing their efficacy in plant disease diagnosis. Transitioning into deep learning, we delve into the paradigm shift that Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and their variants have brought to the field. The central part of this survey centers on sugarcane disease detection, addressing unique challenges in this context. This survey offers valuable insights into advancements in plant disease detection, with a specific focus on sugarcane.