基于最大模糊熵和微粒群的双阈值图像分割  

Double thresholding algorithm for image segmentation based on maximum fuzzy entropy and particle swarm optimization

作　　者：周鲜成[1] 申群太[2] 王俊年[2] 

机构地区：[1]湖南商学院计算机与电子工程系,湖南长沙410205 [2]中南大学信息科学与工程学院,湖南长沙410083

出　　处：《计算机工程与设计》2008年第12期3188-3190,3193,共4页Computer Engineering and Design

基　　金：湖南省自然科学基金项目(06JJ50110)

摘　　要：基于最大模糊熵准则和微粒群算法,提出了一种新的双阈值图像分割方法。该方法通过定义3种模糊隶属度函数,将图像模糊划分为暗、灰和亮3个不同的区域。同时采用微粒群算法搜索最大模糊准则下模糊参数的最优组合,进而确定图像的两个最佳分割阈值。仿真结果表明,该算法具有良好的分割效果和较强的实时处理能力。A double thresholding algorithm for image segmentation based on maximum fuzzy entropy and particle swarm optimization is presented. The image is partion to three parts fuzzily through defming three fuzzy membership functions, including dark, gray and white part. According to the maximum fuzzy entropy principle, the optimal combination of the fuzzy parameters is searched, and the optimal thresholds is determined by particle swarm optimization algorithm. Experimental results show that the proposed method gives better performance, and spends less time.

关 键 词：最大模糊熵 微粒群 阈值 模糊划分 二维灰度直方图 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]