基于隶属度函数平均值的阈值分割算法  

Threshold segmentation algorithm based on the average of membership functions

作　　者：兰蓉[1] 沈文文[1] 

机构地区：[1]西安邮电大学通信与信息工程学院,陕西西安710121

出　　处：《西安邮电大学学报》2015年第2期77-82,共6页Journal of Xi’an University of Posts and Telecommunications

基　　金：国家自然科学基金资助项目(61102095);陕西省科技计划资助项目(2014KJXX-72)

摘　　要：针对图像模糊集模型的构造问题,提出一种基于模糊隶属度函数平均值的阈值分割算法。该算法采用加权平均算子对5种已有的模糊隶属度值进行集结,得到一个模糊隶属度值,从而将图像转化为一个模糊集合,再以指数型模糊散度为目标函数寻找最佳阈值。仿真结果显示了该算法的有效性。For the problem of building a fuzzy set model for an image,a novel threshold segmentation algorithm is presented based on the average of fuzzy membership degree functions.The proposed algorithm uses the weighted averaging operator to obtain a fuzzy membership degree value by aggregating five existing membership degree values for mapping an image to a fuzzy set,and then select the exponential fuzzy divergence as objection function to obtain the optimal threshold.The simulation results show the effectiveness of the proposed algorithm.

关 键 词：阈值分割 隶属度函数 加权平均算子 

分 类 号：TN911.73[电子电信—通信与信息系统]