Leaf Disease Detection using Machine Learning

The cultivation of sugarcane in India is of immense importance to the country's economy; however, it is frequently plagued by various diseases that result in substantial losses in yield. The traditional approach to detecting these diseases by visual inspection is arduous and time-consuming, leading to the development of automated or semi-automated systems capable of identifying plant diseases. This report presents a comprehensive literature review of previous research studies focused on machine learning algorithms for the detection of plant diseases, including StridedNet, LeNet, and VGGNet models, Eigen feature regularization and extraction, active contour models, and backpropagation algorithms. The paper also discusses the use of Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Random Forests for image classification, as well as the dataset employed in the study, which comprises 1378 images of sugarcane.