Classification of Sugarcane Leaf Disease using Deep Learning Algorithms

Early disease identification and detection have been an interest of experts to enhance productivity and performance in agriculture. This study aims to use deep learning algorithms to classify sugarcane diseases using leaf images. Deep learning algorithms are implemented to create models that can classify sugarcane diseases using 16,800 images of training data, 4,800 images for validation tasks, and 2400 images for testing. Results show that the InceptionV4 algorithm outperforms other models in classifying sugarcane leaf diseases at 99.61 accuracy. Different models such as VGG16, ResnetV2-152, and AlexNet achieve high accuracies of 98.88%, 99.23%, and 99.24%, respectively. Hence, this study provides evidence that deep learning models can perform better in classification problems. This study suggests some improvements to further its contribution.