Sugarcane Disease Detection Using CNN-Deep Learning Method
Sammed Abhinandan Upadhye, Maneetkumar Rangnath Dhanvijay, Sudhir Madhav Patil
Abstract
A Machine Learning (ML) technique called deep learning focuses on learning numerous representation layers simultaneously. Deep neural network includes Convolutional Neural Network (CNN). Sugarcane diseases can be prevented and managed more successfully if they are identified properly and quickly. Using a modified deep learning CNN approach this research proposes a method for identifying sugarcane diseases. Sugarcane infections are an issue in the sugar business because they can entirely kill diseased crops, causing financial loss to the farmers if not treated and diagnosed quickly. The study was prompted by the rapid evolution of disease classes and farmer's lack of disease diagnostic and recognition skills. To solve this challenge, machine learning techniques such as computer vision and deep learning can be applied. By separating and categorizing sugarcane images into two groups: healthy and unhealthy/diseased, the trained model is able to fulfill its goal. With a simple CNN with four discrete classes, the analysis shows an accuracy of 98.69% for sugarcane disease detection.