AUTHOR=Deng Ruoling , Tao Ming , Xing Hang , Yang Xiuli , Liu Chuang , Liao Kaifeng , Qi Long 

TITLE=Automatic Diagnosis of Rice Diseases Using Deep Learning

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2021.701038

DOI=10.3389/fpls.2021.701038

ISSN=1664-462X

ABSTRACT=Rice disease has serious effects on the yield, and correct diagnosis of rice diseases is the key to avoid this. However, the existing disease diagnosis methods for rice are not accurate or efficient, and most often special equipment is required. In this study, an automatic diagnosis method was developed and implemented in a smartphone app. The method was developed using deep learning based on a large dataset that contained 33,026 images of 6 types of rice diseases: leaf blast, false smut, neck blast, sheath blight, bacterial stripe disease, and brown spot. The core of the method was the Ensemble Model in which submodels were integrated. Finally, the Ensemble Model was validated using a separate set of images. Results showed that the three best submodels were DenseNet-121, SE-ResNet-50, and ResNeSt-50, in terms of several attributes, including learning rate, precision, recall, and disease recognition accuracy. Therefore, these three submodels were selected and integrated in the Ensemble Model. The Ensemble Model minimized the occurrence of confusion among different types of disease, reducing the misdiagnoses of disease. Using the Ensemble Model to diagnose six types of rice diseases, an overall accuracy of 91% was achieved, which is considered to be reasonably good, considering the appearance similarities among some types of rice disease. The smartphone app allowed the client to use the Ensemble Model on the webserver through the network, which was convenient and efficient for field diagnoses of rice diseases.