Grading method of soybean mosaic disease based on hyperspectral imaging technology
Jiangsheng Gui, Jingyi Fei, Zixian Wu, Xiaping Fu, Alou Diakite
Abstract
Soybean is a crop with a long cultivation history that occupies an important position in agricultural production. Soybean mosaic virus disease (SMV) has caused a rapid decline in soybean yields, causing huge losses to the soybean industry, wherefrom its early detection is particularly important. This study proposes a new classification method for the early SMV, dividing its severity into grades 0, 1 and 2. In the case of a small number of experimental samples of soybeans, this study proposes a combined convolutional neural network and support vector machine (CNN-SVM) method for the early detection of SMV. Experimental results showed that the accuracy of the training set of the CNN-SVM model reached 96.67%, and the accuracy rate of the test set reached 94.17%. The experiment proved the feasibility of using the proposed CNN-SVM model to classify early SMV under the new classification method, and provided a new direction for early SMV detection based on hyperspectral images.