摘要
Taking leaf black spot,anthracnose and leaf blight of Ophiopogon japonicus as the research objects,lesions were separated by K-Means clustering segmentation technology.PCA(principal component analysis)was carried out on the 46-dimensional eigenvectors composed of color,shape and texture features,and then the multi-level classifier designed by SVM(support vector machine)was used to identify lesions.The recognition rate of the developed leaf disease recognition system of O.japonicus achieved 93.3%.The results indicates that the system is of great significance to the prevention and control of O.japonicus diseases and the modernization of O.japonicus industry.
