ABSTRACT

Crop diseases affect crop production, more than 30 billion USD globally. We proposed a classification 

study of crop species and diseases using deep learning algorithms for corn, cucumber, pepper, and 

strawberry. Our study has three steps of species classification, disease detection, and disease classi- 

fication, which is noteworthy for using captured images without additional processes. We designed deep 

learning approach of deep learning convolutional neural networks based on Mask R-CNN model to clas- 

sify crop species. Inception and Resnet models were presented for disease detection and classification 

sequentially. For classification, we trained Mask R-CNN network and achieved loss value of 0.72 for 

crop species classification and segmentation. For disease detection, InceptionV3 and ResNet101-V2 

models were trained for nodes of crop species on 1,500 images of normal and diseased labels, resulting 

in the accuracies of 0.984, 0.969, 0.956, and 0.962 for corn, cucumber, pepper, and strawberry by 

InceptionV3 model with higher accuracy and AUC. For disease classification, InceptionV3 and ResNet 

101-V2 models were trained for nodes of crop species on 1,500 images of diseased label, resulting in 

the accuracies of 0.995 and 0.992 for corn and cucumber by ResNet101 with higher accuracy and AUC 

whereas 0.940 and 0.988 for pepper and strawberry by Inception.