基于FCM和遗传算法的图像模糊聚类分析  

Image fuzzy clustering analysis based on FCM and genetic algorithms

作　　者：娄银霞[1] 程铭[1] 文高进[2] 全惠云[1] 

机构地区：[1]湖南师范大学数学与计算机科学学院,长沙410081 [2]中国科学院深圳先进技术研究院,广东深圳518055

出　　处：《计算机工程与应用》2010年第35期173-176,195,共5页Computer Engineering and Applications

基　　金：国家高技术研究发展计划(863)(No.2009AA01Z302);深圳市科技计划资助项目(No.SY200806300211A)~~

摘　　要：聚类分析在模式识别和图像处理领域中有着极为重要的意义和广泛的应用前景。常用的聚类分析的方法是模糊C均值算法(FCM),但是FCM算法容易陷入局部最优解。提出一种基于FCM和遗传算法对图像进行模糊聚类分析的方法。对输入图像进行纹理特征提取,通过主成分分析法对提取的特征向量进行降维处理,降低图像聚类分析算法的复杂度,提高结果的精确度,结合FCM和遗传算法对图像数据进行模糊聚类分析。实验结果表明该方法可以得到较好的分类效果。Cluster analysis has great importance and broad application prospects in the fields of pattern recognition and im-age processing.Commonly used method of cluster analysis is the fuzzy C-means algorithm（FCM）.The FCM algorithm easily traps into local optimal solution.An algorithm combining FCM with genetic algorithms is introduced for image fuzzy cluster-ing analysis.The input image texture features are extracted,and the dimension reduction of extracted feature vector is pro-cessed through principal component analysist,he image of the cluster analysis algorithm complexity is reduced and the accu-racy of the results is improved.Image data of the fuzzy cluster is analyzed combined with genetic algorithm FCM.The experi-ment results show that this method can get a better clustering effect.

关 键 词：模糊C均值聚类 遗传算法 模糊聚类 聚类分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]