基于模糊隶属度中值的阈值分割算法  

Threshold segmentation algorithm based on median of fuzzy membership degree

作　　者：史露娜 兰蓉[1] SHI Luna;LAN Rong(Xi’an University of Posts and Telecommunications,Xi’an 710061,China)

机构地区：[1]西安邮电大学,陕西西安710061

出　　处：《现代电子技术》2018年第11期40-45,共6页Modern Electronics Technique

基　　金：国家自然科学基金资助项目(61571361);陕西省教育厅科学研究计划资助项目(16JK1709);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中值的阈值分割算法。该算法选取有代表性的几种隶属度函数在给定灰度处的中值作为新的隶属度值,即提取多个隶属度值的一维统计特征,将灰度图像转化为一个模糊集合,再以α-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。A threshold segmentation algorithm based on median of fuzzy membership degree is proposed to construct a fuzzy set model for an image. The median（at a preset gray level）of several representative membership-degree functions is selected in the algorithm as the new membership degree value,that is,the one-dimensional statistical characteristic of multiple membership degree values is extracted to convert the gray image into a fuzzy set,and then search the optimum threshold by taking α-type fuzzy divergence as the objective function. The simulation results show that the algorithm is effective.

关 键 词：阈值分割 隶属度函数 模糊集 中值 模糊散度 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]