基于鸡群优化算法的SAR图像快速分割  

SAR image fast segmentation based on chicken swarm optimization algorithm

作　　者：梁建慧 王丽芳[1] 蒋泽军[1] 马苗[3] Liang Jianhui;Wang Lifang;Jiang Zejun;Ma Miao(School of Computer Science,Northwestern Polytechnical University,Xi’an 710129,China;Institute of Tropical Agriculture&Forestry,Hainan University,Danzhou Hainan 571737,China;School of Computer Science,Shaanxi Normal University,Xi’an 710062,China)

机构地区：[1]西北工业大学计算机学院,西安710129 [2]海南大学热带农林学院,海南儋州571737 [3]陕西师范大学计算机科学学院,西安710062

出　　处：《计算机应用研究》2018年第9期2842-2844,2852,共4页Application Research of Computers

基　　金：海南省自然科学基金资助项目(618QN220);海南大学2017年度教育教学改革研究项目(hdjy1730);国家自然科学基金资助项目(61373120);陕西省农业科技创新与攻关项目(2016NY-176);陕西师范大学中央高校基本科研业务费资助项目(GK201703054)

摘　　要：为提高SAR图像分割的速度和质量,利用鸡群优化算法,提出了一种SAR图像快速分割方法。该方法使用二维灰色Otsu模型作为鸡群优化算法的适应度函数,利用鸡群中公鸡、母鸡和小鸡的角色分工、协同工作快速逼近最佳阈值。实验结果表明,该方法在收敛速度和分割效果两方面均优于基于遗传算法、人工鱼群算法等群体智能优化算法的分割方法。In order to increase the speed and the accuracy of SAR image segmentation,this paper proposed a SAR image fast segmentation method,which integrated chicken swarm optimization algorithm.It used a two-dimensional grey Otsu module as the fitness function in chicken swarm optimization algorithm.And this method located the best threshold gradually and quickly by virtue of the role division of chickens and teamwork of roosters,hens and chicks.Experimental results show that the method is superior to some segmentation methods based on genetic algorithm and artificial fish swarm algorithm in convergence and segmentation effects.

关 键 词：图像分割 鸡群优化算法 群体智能 SAR图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]