线性判别分析（LDA）用于特征选择，可以对数据集或者图像提取有用特征，用于分类或者聚类等机器学习应用中-Linear Discriminant Analysis (LDA) for feature selection, application in dataset or image feature extraction, for classification or clustering applications in machine learning

K-meansK均值聚类在无监督的情况下选择图像特征的算法-K-meansK means clustering in the case of unsupervised image feature selection algorithm

：将信息论中熵的概念应用到特征选择中，定义了两种信息测度评价特征——误差熵和混叠熵，然后阐述了两种定义的不 用物理意义，分析了计算熵中最关键的区间划分问题，并提出一种较好的区间划分方法。-: The concept of entropy in information theory applied to feature selection, the definition of information measure evaluation of two features- error entro