机构地区: 天津大学电子信息工程学院
出 处: 《模式识别与人工智能》 2003年第2期208-212,共5页
摘 要: 本文给出了一种基于最优线性变换和支持矢量机(Support Vector Machine,SVM)的合成孔径雷达(Synthetic Aperture Radar,SAR)自动目标识别方法。该方法首先对目标图像做线性变换使目标的类间距加大,类内距减小,然后利用SVM分类器实现SAR目标的自动分类。实验结果表明该方法具有良好的识别率和推广性能。 In this paper, an efficient SAR ATR (Synthetic Aperture Radar Automatic Target Recognition) approach based on optimal linear transform and SVM is proposed. First, linear transform of SAR images is performed to maximize the distance between classes and to minimize the distance within classes, then SVM is used to implement target classification. Experimental results illustrate the performance of the proposed approach.