基于改进量子遗传优化的模糊C均值聚类图像分割  

Fuzzy C Mean Clustering Based on Improved Quantum Genetic Algorithm for Image Segmentation

作　　者：逯清玉[1] 张晓明[2] 

机构地区：[1]青海建筑职业技术学院基础及素质教育部,青海西宁810012 [2]长春建筑学院基础教学部,吉林长春130607

出　　处：《数学的实践与认识》2016年第17期174-181,共8页Mathematics in Practice and Theory

摘　　要：针对模糊C均值聚类算法对初始聚类中心值敏感和抗噪声能力差的问题,提出一种基于改进的量子遗传优化初始聚类中心的算法,改进双链编码的量子遗传算法增加了全局搜索能力,改变传统的FCM算法计算迭代慢和易陷入局部极值的问题.同时引入空间邻域信息,利用加权隶属度矩阵建立适应度函数来改善对噪声的鲁棒性,实验结果表明,算法具有很好的分割效果和较强的抗噪能力.As fuzzy C mean clustering algorithm is sensitive to initial clustering center value and the anti noise ability,an improved quantum genetic algorithm is proposed by initial cluster center,which improves global searching ability of quantum genetic algorithm,and changes traditional FCM algorithm to solve slow and easy problem to fall into local extremum.At the same time,the spatial neighborhood information is introduced,and the fitness function is established to improve the robustness to noise.Experimental results show that the proposed algorithm has a good segmentation effect and strong anti noise ability.

关 键 词：模糊C均值 空间邻域信息 双链量子遗传 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]