Deep Learning-based Approach for Leaf Disease of Sugarcane Classification

The primary crop used to produce sugar and ethanol in the globe is sugarcane. One issue in the sugar sector is if sugarcane illnesses are not treated and diagnosed early, they can eradicate growing crops that are infected with the disease, costing small-scale farmers money. The continuously growing categories of illnesses and farmers’ limited capacity for disease diagnosis and identification served as the impetus for this investigation. Deep learning techniques combined with computer vision and machine learning provide a solution to this problem. In this work, a deep learning model with a 97% accuracy rate was constructed and evaluated using 1200 photos of healthy and sick sugarcane leaves. By distinguishing between classes of healthy and ailing or diseased sugarcane leaves in photographs of sugarcane, the trained model successfully performed its objective. This study recommends employing a deep learning system to help farmers recognize and classify sugarcane illnesses.