基于数学形态学的聚类分析  

Cluster Analysis Based on Mathematical Morphology

作　　者：罗会兰[1] 孔繁胜[1] 杨小兵[1] 刘必红[1] 

机构地区：[1]浙江大学人工智能研究所

出　　处：《模式识别与人工智能》2006年第6期727-733,共7页Pattern Recognition and Artificial Intelligence

基　　金：江西省自然科学基金资助项目(No.0411046)

摘　　要：数学形态学广泛应用于图像识别之中,经典的聚类方法在聚类形状复杂时难于获得满意的结果。本文提出一种新的基于数学形态运算的聚类方法,通过合理选择离散化参数和结构元素,这种基于分级数学形态操作序列的聚类方法能较好地将各个簇分离开来,实验证明此方法比传统方法效果更好,并且能有效确定聚类数。Mathematical morphology has been widely used in image analysis. Classical clustering methods often fail to deliver satisfactory results, especially when clusters have arbitrary shapes. Through some techniques for selecting discretization parameters and structural elements, a new approach to cluster analysis is proposed, which is based on the mathematical morphology operations. Clusters are well separated by means of hierarchical mathematical morphology procedures. Experimental results demonstrate that the proposed clustering algorithm clusters data better than the classical clustering algorithms, and an optimal number of clusters could be found.

关 键 词：数学形态学 聚类分析 膨胀 腐蚀 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]