两向二维最大子类散度差鉴别分析及其在SAR目标识别中的应用  

Two-directional Two-dimensional Maximum Clustering-based Scatter Discriminant Analysis and Its Application to SAR Target Recognition

作　　者：胡利平[1] 刘宏伟[1] 尹奎英[1] 吴顺君[1] 

机构地区：[1]西安电子科技大学雷达信号处理国家重点实验室,陕西西安710071

出　　处：《航空学报》2009年第12期2380-2386,共7页Acta Aeronautica et Astronautica Sinica

基　　金：国家自然科学基金(60072140)

摘　　要：针对Fisher线性判决分析(FLDA)在图像识别应用中遇到的小样本问题,提出了两向二维最大子类散度差((2D)2MCSD)鉴别分析的图像特征提取方法。首先找到每类数据的子类划分,再根据这些子类构造基于二维图像矩阵的子类类间和子类类内散布矩阵,最后用子类类间与子类类内散布之差作为鉴别准则求取投影矢量。该方法可以处理多模分布问题,从根本上避免了矩阵求逆和小样本问题,加快了特征抽取的速度,且同时对图像行和列进行压缩,克服了二维最大子类散度差(2DMCSD)鉴别分析和另一种形式的2DMCSD(Alternate 2DMCSD)的特征维数较大的问题。基于美国运动和静止目标获取与识别(MSTAR)公共数据库提供的实测数据的实验结果表明:本文方法的性能优于现有的子空间方法;与2DMCSD和Alter-nate 2DMCSD相比,可大大降低特征维数、提高识别性能。To solve the small sample size（SSS） problem of Fisher linear discriminant analysis（FLDA） when it is applied to image recognition tasks,a novel image feature extraction technique is proposed which is called two-directional two-dimensional maximum clustering-based scatter difference（（2D）2MCSD） discriminant analysis.In this method,the possible clusters for each class are first found,and then the between-cluster and within-cluster scatter matrices are constructed from the 2D image matrices based on these clusters. Finally,projection vectors are sought by taking the difference of between-class scatter and within-class scatter as the discriminant criterion. Thus the method can not only deal with multimodal distribution problems but also avoid inverse matrix calculation and SSS problems, and increase the efficiency of feature extraction. Moreover, the （2D）2 MCSD compresses image rows and columns simultaneously, thus overcoming the problem of too many features of 2DMCSD and Alternate 2DMCSD. Experiments on a moving and stationary target acquisition and recognition （MSTAR） public database demonstrate that the （2D）2 MCSD is more efficient than some existing subspace methods. Furthermore, compared with 2DMCSD and Alternate 2DMCSD, （2D）^2 MCSD achieves higher recognition rates with much less memory requirements.

关 键 词：目标识别 合成孔径雷达 子类判决分析 最大散度差 Fisher线性判决分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP311.1[自动化与计算机技术—计算机科学与技术]