基于改进BBO算法的FCM图像分割方法  

FCM image segmentation method based on improved BBO algorithm

作　　者：李薇 胡晓辉[1] 王鸿闯 LI Wei;HU Xiao-hui;WANG Hong-chuang(School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhan 730070,China)

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《传感器与微系统》2018年第10期57-59,共3页Transducer and Microsystem Technologies

基　　金：甘肃省科技计划资助项目(144NKCA040)

摘　　要：针对模糊C均值(FCM)算法进行图像分割时初始聚类中心选取困难的问题,提出了一种基于改进的生物地理学(BBO)优化算法的FCM图像分割方法,提高最优解的全局搜索性能。不同于传统的BBO算法,改进的BBO算法使用新的迁移策略和变异算子。为了评估所提出的方法,同时进行了基于遗传算法以及标准BBO算法的FCM图像分割实验,实验结果表明:相对于其他2种算法,提出的方法具有良好的收敛稳定性,可以有效缩短迭代时间,提高分割准确性。Aiming at the difficulty of selecting initial cluster centers in image segmentation based on fuzzy C-mean（ FCM） algorithm,a FCM image segmentation method based on improved biogeography optimization（ BBO）algorithm is proposed. The improved BBO algorithm is used to improve the global search performance of the optimal solution. Unlike the traditional BBO algorithm,the improved BBO algorithm uses new migration strategy and mutation operator. To evaluate the method,the FCM image segmentation experiments based on the genetic algorithm and the standard BBO algorithm is also carried out,when the proposed method is used to segment typical images. Experimental results show that the proposed method has good convergence stability,can effectively shorten the iteration time and improve the segmentation accuracy.

关 键 词：图像分割 生物地理学优化算法 变异算子 模糊C均值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]