Sugarcane Disease Recognition using Deep Learning

Abstract

Sugarcane is a vital crop worldwide and the main source of sugar and ethanol. One problem in the sugar industry is sugarcane diseases that leads in eradicating growing crops infested with the disease resulting in the financial loss of small-scale farmers if these diseases are not treated and detected early. With the fast-growing classes of diseases and inadequate know-how of farmers in identification and recognition of diseases was the motivation in conducting this study. Machine learning through computer vision using deep learning techniques provides a solution to solve this problem. This study trained and test a deep learning model consisting of 13,842 sugarcane image dataset of disease infected leaves and healthy leaves achieving an accuracy of 95%. The trained model achieved its purpose by detecting and classifying sugarcane images into healthy and unhealthy or diseased class of sugarcane leaves. Therefore, this paper provides an idea of helping farmers with the aid of deep learning algorithm in detecting and classifying sugarcane diseases.