在模糊c -均值聚类的基础上选择训练样本,可以提高训练样本的准确度,满足了训练样本所需的单一性原则。
Selecting train sample on the basis of fuzzy C-mean clustering can improve accuracy of train sample, singleness of train samples can be satisfied.
揭示出植被分类的原则从单一性向综合性,分类方法从外貌分类向数量分类的发展趋势。
It also revealed the trend that the principle of vegetation classification is becoming comprehensive and classification methods are utilizing numerical classification instead of exterior one.
应用推荐