Based on the features of plant disease image, vector median filter was firstly applied to remove noise of the acquired color images of grape leaf with disease. Then texture features and color features of color image of leaf with disease were extracted as feature vector. And by using Mercer kernel functions, the data in the original space was maped to a high-dimensional feature space in which the data has been clustered efficiently. The precision of four kinds of experimental maize diseases recognition is 82.5%, and kernel K-means clustering algorithm suited the plant leaf disease classification recognition.
参考文献
相似文献
引证文献
引用本文
王守志,何东健,李文,王艳春.基于核K—均值聚类算法的植物叶部病害识[J].农业机械学报,2009,40(3):152-155. Leaf Disease Recognition Based on Kernel K-means Clustering Algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery,2009,40(3):152-155.