中文说明：聚类分析是无监督模式识别中的一种重要方法 ,已广泛应用于数据挖掘 、图像处理、计算机视觉 、生物信息和文本分析中。聚类算法就是将一组分布未知的数据进行分类, 其目的是寻找隐藏在数据中的结构, 并按照某种相似程度的度量, 尽可能地使具有相同性质的数据归于同一类 作为经典k-means算法的一个变种，具有很强的代表性。intelligent kmeans算法的实现代码。可以自动识别k的个数，并且可以初始化初始中心的选择，可以取得较好的聚类效果。
English Description：
Cluster analysis is an important method of unsupervised pattern recognition, are widely used in data mining, image processing and computer visionSleep, bioinformatics, and text analysis. Clustering algorithm is aSet of classified data distribution is unknown, its purpose was to search for hiddenIn data structures, and in accordance with a similarity measure, as far as possibleTo ensure that data are of the same nature attributed to the same type ofAs a variant of the classic k-means algorithm, has a strong representation. Intelligent code of the kmeans algorithm. Can automatically identify the number k, and initializes the center of choice, you can achieve good clustering results.