基于差准则的二维非参数特征分析的SAR目标识别

提出一种基于差准则的二维非参数特征分析(2 dimensional nonparametric feature analysis based on difference criterion,2DDNFA)的图像特征提取方法,它结合了二维线性判决分析(2-dimensional linear discriminant analysis,2DLDA)、最大散度差(maximum scatter difference,MSD)、非参数判决分析(nonparametric feature analysis,NFA)3种方法的思想。首先利用二维图像样本的近邻样本构造类内、类间散布矩阵,再基于差准则计算投影矩阵,最后将二维图像向投影矩阵投影得到特征矩阵。基于实测合成孔径雷达(synthetic aperture radar,SAR)数据的实验结果表明,方法的性能优于基于Fisher准则的2DLDA、二维非参数特征分析(2 dimension nonparametric feature analysis, 2DNFA)方法、也优于基于差准则的二维最大散度差(2-dimensional maximum scatter difference,2DMSD)鉴别分析方法。

2-dimensional nonparametric feature analysis based on difference#br# criterion and SAR target recognition

A novel image feature extraction method called 2 dimensional nonparametric feature analysis based on difference criterion (2DDNFA) is proposed, which combines the ideas of 2 dimensional linear discriminant analysis (2DLDA), maximum scatter difference (MSD), and nonparametric feature analysis (NFA). Firstly, the between class and within class scatter matrices are constructed by using the neighbors of the samples in the 2 dimensional image space. And then, the projection matrix is computed based on the difference criterion. Finally, the feature matrix of an image is obtained by projecting it on the projection matrix. Experiments conducted on the measuring synthetic aperture radar (SAR) data demonstrate that the proposed method is more efficient than the methods, such as 2DLDA, 2 dimensional nonparametric feature analysis (2DNFA), and 2 dimensional maximum scatter difference (2DMSD).