摘要
由于存在相干斑噪声的影响,使得常规的图像分割技术应用于SAR图像时,效果往往较差。该文提出一种新人工免疫系统SAR图像分割算法,算法首先提取每幅图像的纹理特征,并对其进行实数编码,然后通过借鉴生物学免疫系统的抗体克隆选择机理,构造适合于图像分割的克隆算子,以较快的收敛速度优化目标函数。实验结果表明,新算法是一种有效的SAR图像区域分割方法。
Because of the multiplicative nature of the speckle noise in SAR images, it is difficult to solve SAR image segmentation problems using general image segmentation technique. A novel SAR image segmentation algorithm based on an artificial immune system is proposed. After extracting texture features from an image and encoding them with real numbers, it determines partitioning of the feature vectors by optimizing the objective function based on clonal operator. The experimental results show that the novel algorithm is feasible and effective for SAR image segmentation.
出处
《电子与信息学报》
EI
CSCD
北大核心
2009年第7期1749-1752,共4页
Journal of Electronics & Information Technology
基金
国家自然科学基金(60703107
60703108)
国家863计划项目(2008AA12Z2475853)
国家973计划项目(2006CB705700)资助课题
关键词
合成孔径雷达
图像分割
免疫克隆
聚类
Synthetic Aperture Radar（SAR）
Image segmentation
Immune clonal
Clustering
