摘要
MSTAR目标图像分割是研究SAR图像分割的重要内容,基于最大熵原理,利用二维直方图设计适应度函数,借助遗传算法实现自适应阈值选取,以确定每个像素点的归属,经实际图像测试,对于含噪SAR图像中目标、背景和阴影的分割具有很好的效果,抑噪功能强。
The segmentation of target and background is an important content of SAR image segmentation. The authors designed an adaptation level function based on two-dimensional histogram and maximum entropy theory, and put forward a new segmentation algorithm to seek self-adaptive optimum threshold value by use of the genetic algorithm. The experimentation shows that it has a good effect for target, background and shadow segmentation of speckled SAR image.
出处
《电光与控制》
北大核心
2007年第4期63-65,69,共4页
Electronics Optics & Control
基金
国家自然科学基金资助项目(60272022)
关键词
合成孔径雷达
遗传算法
熵
图像分割
自动目标识别
synthetic aperture radar
genetic algorithm
entropy
image segmentation
automatic target recognition
