Res-VGG: A Novel Model for Plant Disease Detection by Fusing VGG16 and ResNet Models

Abstract

Agriculture is one of the major growing sectors in India, and plant disease is the key factor that affects the economy of the country to a large extend. Plant disease management has become a challenging task to ensure the food safety and sustainability of agriculture. Deep learning (DL) has recently made some good walk-through in the field of image identification and classification. In this article, we have proposed a new model called Res-VGG that hybridized two different DL models such as VGG16 and ResNet. This model has been used to detect and categorize the symptoms of plant diseases. In our proposed model, we have used a total of 12 layers consisting of 9 convolutional layers, two fully connected layers, and one softmax layer. The effectiveness of this proposed model has been tested and validated using Plant Village dataset. The experimental analysis reveals that the proposed model is superior over the existing models in terms of disease identification so that effective preventive measures can be taken for eliminating these diseases, thus removing the problem of food security.