Artificial Intelligence Framework for Sugarcane Diseases Classification using Convolutional neural Network

Abstract

In many regions of the world, plant disorders have long been a threat to crop development and agricultural production, negatively affecting the availability of food for people. The best organised sector of agriculture is sugarcane cultivation. It is the first crop that farmers grow because of the ideal conditions for its development. It is closely related to the sugar sector and has a significant impact on the economy of several countries. Of all the crops grown for commercial purposes, sugarcane has the highest production value. In contrast, a different type of diseases can affect the quality and productivity of the crop. Growers can detect some of them by visual inspection of the leaves. Unfortunately, the majority of infections go undetected, causing farmers to suffer significant losses. To reduce the damage caused by an infestation, it is important to determine the type of infestation. So, we proposed a Deep Learning (DL) model that uses images of diseased leaves to train the model to recognise a specific disease affecting the sugarcane plant. In this work, we have used bacterial blight, red rot, red rust and healthy leaf images. The method used two convolutional neural networks to classify the 851 sugarcane leaf images. As a result, Resnet50 achieved the highest accuracy of and 99.70% for binary classification (normal and abnormal images). The trained model achieved its goal by identifying photos of sugarcane and classifying them into classes of healthy and diseased leaves. As a result, this research provides a proposal for using deep learning algorithms to help farmers detect and categorise sugarcane infections. Finally, we have applied an DL visualization technique such as gradient class activation map, occlusion sensitivity, and local interpretable model-agnostic to differentiate and understanding the classification process by highlighting area that is more used for the classification.