模式识别中的k近邻算法，经过测试，运行结果很好。
最小距离分类器 : 它将各类训练样本划分成若干子类，并在 每个子类中确定代表点 。测试样本的类别则以其与这些代表点距离最近作决策。该方法的缺点是所选择的代表点并不一定能很好地代表各类，其后果将使错误率增加。(The k nearest neighbor algorithm in pattern recognition has been tested and the result is very good.
Minimum distance classifier: it divides all kinds of training samples into several sub classes and identifies the representative points in each sub class. The categories of test samples are made recently by making decisions with these representatives. The disadvantage of this method is that the selected representative points do not necessarily represent the various types well, and the consequences will increase the error rate.)