现代雷达2011，Vol.33Issue(9)：37-41,5.
幂变换在一维距离像目标识别中的作用分析
Performance of Power Transform in High Resolution Range Profiles Target Identification
摘要
Abstract
Power transform is a nonlinear pretreatment method. Random variables which are obedient to any probability distribution are more close to Cuass distribution after power transform, so that classifiers based on Cuass distribution can be used. Hie recognition rate of high resolution range profiles can be improved obviously. It is mainly analysed that how we should decide the power transform coefficient in order to get good recognition results. Hie range profiles in different noise condition are processed using different power transform coefficients, and then classified with radial basis function classifiers. According to the real data processing results, It is known that we should decide power transform coefficients in accordance with the signal-to-noise ratio.关键词
幂变换/一维距离像/径向基函数分类器Key words
power transform coefficient/ high resolution range profiles/ radial basis function classifier分类
信息技术与安全科学引用本文复制引用
徐海丽,王洋..幂变换在一维距离像目标识别中的作用分析[J].现代雷达,2011,33(9):37-41,5.
