The local feature based representation could be obtained by choosing suitable dimension of the feature subspace in NMF.
非负矩阵分解过程中，适当地选取特征空间的维数能够获得原始数据的局部特征。
Then, the performance of two SVD algorithms and feature subspace radar target recognition algorithm based on SVD are evaluated according to real data of planes.
进而将两种SVD算法应用在特征子空间雷达目标一维距离像识别法中，使用实测数据对其进行速度验证和性能评估。
This thesis studies the feature selection method of HRRP and proposes a RATR method in target subspace based on the analysis of noise-match in HRRP space.
基于对HRRP空间雷达自动目标识别中冗余噪声匹配的分析，研究了高分辨距离像的特征选择方法，提出了一种基于目标子空间的雷达自动目标识别方法。
The optimal subspace is used to extract feature of target for improving classification performance.
利用最优子空间能够提取到更优的特征，改善目标识别性能。
The feature points are clustered in this subspace using a graph spectral approach.
的特征点都聚集在此子空间使用的光谱的曲线图的方法。
This paper deals with all above three steps, most work is described as follows: (1) We present a method of face detection based on subspace feature.
本文在人脸识别的三个主要环节上均进行了研究工作，主要工作体现在以下几个方面：(1)提出了基于子空间特征的人脸检测方法。
It applies WP translate to get energy from subspace and select the best WP bases with classification distance criterion. The energy has bigger distance coefficient in best WP bases is the feature.
该方法应用小波包变换提取信号各子空间的能量，以能量分类距离标准选取最佳小波包基，最佳小波包基上距离系数大的能量作为特征值。
It applies WP translate to get energy from subspace and select the best WP bases with classification distance criterion. The energy has bigger distance coefficient in best WP bases is the feature.
该方法应用小波包变换提取信号各子空间的能量，以能量分类距离标准选取最佳小波包基，最佳小波包基上距离系数大的能量作为特征值。
应用推荐