基于目标函数的直觉模糊聚类图像分割方法  

Research on the Intuitionistic Fuzzy Clustering Image Segmentation Method based on Objective Function

作　　者：向灿群 欧先锋[1,2] 张国云[1,2] 湛西羊 罗百通 潘建武[1,2] 李交杰[1,2] XIANG Canqun OU Xianfeng ZHANG Guoyurt ZHAN Xiyang LUO Baitong PAN jtanwu LI Jiaojte(College of Information ＆ Communication Engineering Key Laboratory of Optimization ＆ Control for Complex Systems, Hunan Institute of Science and Technology, Yueyang 414006, China College of Information Engineering, Shenzhen University, Shenzhen 518060, China)

机构地区：[1]湖南理工学院信息与通信工程学院,湖南岳阳414006 [2]湖南理工学院复杂系统优化与控制湖南省普通高等学校重点实验室,湖南岳阳414006 [3]深圳大学信息工程学院,广东深圳518060

出　　处：《成都工业学院学报》2017年第3期1-5,共5页Journal of Chengdu Technological University

基　　金：国家自然科学基金项目(51704115);湖南省自然科学基金项目(2017JJ3099);湖南省科技计划项目(2016TP1021)

摘　　要：针对模糊C-均值聚类分割算法易丢失图像细节的问题,提出一种改进的直觉模糊C-均值聚类算法。该算法将纹理特征和直觉指数引入到目标函数,并给出改进的聚类目标函数,对其聚类目标函数最优化推导并得到新的隶属度和聚类中心迭代表达式,并设计相应的图像分割算法,实验结果表明了算法的有效性。Due to the Fuzzy C-means clustering algorithm is easy to lose image details, an improved intuitionistic fuzzy C-means clustering algorithm based on FCM was proposed. By using this algorithm, the texture feature and intuitive index were introduced into the objective function, and a modified clustering objective function can be get. Then, this clustering objective function was OPtimized to obtain new clustering center and membership iterative expressions. Based on these, the corresponding image segmentation algorithm was presented.The experimental results show the feasibility of the algorithm.

关 键 词：直觉模糊C-均值聚类 直觉模糊集 纹理特征 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]