一个基于谱图分割的简单聚类算法

A Simple Algorithm Based on Spectral Graph Partition

目前谱聚类在文本分类、图像分割和信息检索等领域的应用越来越引起研究者的重视,并取得了一定的成果.但是,大多数已有的谱聚类算法需要事先给定聚类数.在k means算法、EM等聚类方法中也存在相似的问题.在此介绍了一种简单的容易实现的谱聚类算法,可以自动确定合适的聚类数.实验表明本算法结果很好.

Motivated by applications such as document classification and image segmentation, spectral clustering has attracted a great deal of attention of many researchers. However, most existing algorithms on spectral clustering are not able to determine the number of clusters. It is same to other approaches on clustering such as k-means and EM.It presents a simple, easily implemented method on spectral clustering to automatically find the suitable value of clustering number and gives superior performance on experiment.