Potato Leaf Disease Classification Using Deep Learning Approach

Abstract

Potato is one of the staple foods that widely consumed, becoming the 4th staple food consumed throughout the world. Also, the world demand for potato is increasing significantly, primarily due to the world pandemic coronavirus. However, potato diseases are the leading cause of the decline in the quality and quantity of the harvest. Inappropriate classification and late detection of the disease's type will drastically worsen the plant conditions. Fortunately, several diseases in potato plants can be identified based on leaf conditions. Therefore, in this paper, we present a system to classify the four types of diseases in potato plants based on leaf conditions by utilising deep learning using the VGG16 and VGG19 convolutional neural network architecture model to obtain an accurate classification system. This experiment has achieved an average accuracy of 91%, which indicates the feasibility of the deep neural network approach.