SAR image target segmentation based on entropy maximization and morphology  

作　　者：BaiZhengyao LiuZhoufeng HePeikun 

机构地区：[1]DepartmentofElectronicEngineering,BeijingInstituteofTechnology,Beijing100081,P.RChina//DepartmentofElectronicEngineering,YurmanUniversity,Kunming650091,P.R.China [2]DepartmentofElectronicEngineering,BeijingInstituteofTechnology,Beijing100081,P.RChina

出　　处：《Journal of Systems Engineering and Electronics》2004年第4期484-487,共4页系统工程与电子技术（英文版）

摘　　要：Entropy maximization thresholding is a simple, effective image segmentation method. The relation between the histogram entropy and the gray level of an image is analyzed. An approach, which speeds the computation of optimal threshold based on entropy maximization, is proposed. The suggested method has been applied to the synthetic aperture radar (SAR) image targets segmentation. Mathematical morphology works well in reducing the residual noise.

关 键 词：SAR 图像分割 熵最大化 阈值 合成孔径雷达 

分 类 号：TN958[电子电信—信号与信息处理] TN957.52[电子电信—信息与通信工程]