Cross grouping strategy based 2DPCA method for face recognition

Grouping strategy exactly specifies the form of covariance matrix, therefore it is very essential. Most 2DPCA methods use the original 2D image matrices to form the covariance matrix which actually means that the strategy is to group the random variables by row or column of the input image. Because of their grouping strategies these methods have two main drawbacks. Firstly, 2DPCA and some of its variants such as A2DPCA, DiaPCA and MatPCA preserve only the covariance information between the elements of these groups. This directly implies that 2DPCA and these variants eliminate some covariance information while PCA preserves such information that can be useful for recognition. Secondly, all the existing methods suffer from the relatively high intra-group correlation, since the random variables in a row, column, or a block are closely located and highly correlated. To overcome such drawbacks we propose a novel grouping strategy named cross grouping strategy. The algorithm focuses on reducing the redundancy among the row and the column vectors of the image matrix. While doing this the algorithm completely preserves the covariance information of PCA between local geometric structures in the image matrix which is partially maintained in 2DPCA and its variants. And also in the proposed study intra-group correlation is weak according to the 2DPCA and its variants because the random variables spread over the whole face image. These make the proposed algorithm superior to 2DPCA and its variants. In order to achieve this, image cross-covariance matrix is calculated from the summation of the outer products of the column and the row vectors of all images. The singular value decomposition (SVD) is then applied to the image cross-covariance matrix. The right and the left singular vectors of SVD of the image cross-covariance matrix are used as the optimal projective vectors. Further in order to reduce the dimension LDA is applied on the feature space of the proposed method that is proposed method + LDA. The exhaustive experimental results demonstrate that proposed grouping strategy for 2DPCA is superior to 2DPCA, its specified variants and PCA, and proposed method outperforms bi-directional PCA + LDA.     

A quick deviation zone fitting in coordinate metrology of NURBS surfaces using principle component analysis

Evaluation of the tolerance zone using discrete measured points plays a critical role in today’s manufacturing, metrology, and many industrial applications. The deviation zone is typically evaluated using a fitting method that locates an ideal desired geometry corresponding to a set of measured points while a function of the Euclidean distances of the measured points to the ideal surface becomes minimum. This paper presents a quick and reliable algorithm called Dynamic Principle Component Alignment (DPCA) for fitting complex surfaces to the coordinate metrology measured points using the information that is dynamically generated by Principal Component Analysis (PCA) of the measurement data and the corresponding fitted geometry. The developed algorithm efficiently eliminates the necessity for applying commonly used optimization methods for the fitting (localization) process, which decreases the computational cost and uncertainty of the evaluation process. Moreover, DPCA is very reliable and practical in coordinate metrology with large data sets in processes such as laser scanning and other optical methods. The results show that the proposed methodology more accurately finds fitting parameters in comparison with the other commonly used methods while the computational cost is considerably reduced.     

一种新的二维特征抽取算法及应用

二维主成分分析方法是直接利用二维图像来构建方差矩阵的。为了充分利用样本类别信息,文章以类间散布矩阵特征向量作为投影方向进行特征抽取。首先用2DPCA先作一次横向压缩,对抽取出的特征矩阵再用2DPCA作一次纵向压缩。与传统二维主成分算法比较,极大压缩了特征的维数,加快了分类速度,提高了识别率。用ORL人脸数据库进行了实验验证,证明了本方法的可行性。     

2DPCA-SIFT:一种有效的局部特征描述方法

PCA-SIFT （Principal component analysis—scale invariant feature transform）方法通过对归一化梯度向量进行PCA降维,在保留特征不变性的同时,有效地降低了特征矢量的维数,从而提高了局部特征的匹配速度. 但PCA-SIFT中对本征向量空间的求解非常耗时,极大地限制了PCA-SIFT的灵活性与应用范围. 本文提出采用2DPCA对梯度向量块进行降维的特征描述方法. 该方法相比于PCA-SIFT,可以快速地求解本征空间. 实验结果表明:2DPCA-SIFT在多种图像变换匹配和图像检索实验中可以实现与PCA-SIFT相当的性能,并且从计算效率上看,2DPCA-SIFT具有更好的扩展性.     

一种改进的2DPCA方法在人脸识别中的应用

为了提高二维主成份分析(2DPCA)方法在人脸识别中的识别率,提出了一种改进的2DPCA和分块图像相结合的人脸识别方法。该方法根据类内图像与该类平均图像的距离,引入加权函数,重新定义2DPCA的总体散布矩阵,并应用到分块图像中,对训练样本子图像采用改进的2DPCA方法进行特征提取,实现模式分类。在ORL标准人脸库上的实验结果表明,它可以有效地提高识别率。     

基于人脸表情特征的情感交互系统*

设计了一套基于人脸表情特征的情感交互系统(情感虚拟人),关键技术分别为情感识别、情感计算、情感合成与输出三个方面。情感识别部分首先采用特征块的方法对面部静态表情图形进行预处理,然后利用二维主元分析(2DPCA)提取特征,最后利用多级量子神经网络分类器实现七类表情识别分类;在情感计算部分建立了隐马尔可夫情感模型(HMM),并且用改进的遗传算法估计模型中的参数;在情感合成与输出阶段,首先采用NURBS曲面和面片相结合的算法,建立人脸三维网格模型,然后采用关键帧技术,实现了符合人类行为规律的连续表情动画。最后完成了基于人脸表情特征的情感交互系统的设计。     

Noise amplification analysis and comparison of two periodic nonuniform sampling reconstruction methods used in DPCA SAR

General Sampling Expansion Reconstruction Method （GSERM） and Digital Spectrum Reconstruction Method （DSRM）, which prove effective to reconstruct azimuth signal of Displaced Phase Center Apertures （DPCA） Synthetic Aperture Radar （SAR） system from its Periodic Non-Uniform Sampling （PNUS） data sequences, would amplify the noise and sidelobe clutter simultaneously in the reconstruction. This paper formulates the relation of the system transfer matrixes of the above two methods, gives the properties, such as periodicity, symmetry, and time-shift property, of their Noise and Sidelobe Clutter Amplification Factor （NSCAF）, and discovers that DSRM is more sensitive than GSERM in the white noise environment. In addition, criteria based on initial sampling point analysis for the robust PRF selection are suggested. Computer simulation results support these conclusions.     

基于模糊C-均值聚类的小波分析人脸识别

提出了一种基于改进的模糊C-均值聚类分类器的不完全小波分析人脸识别方法。实验证明,该文提出的方法能够提高人脸识别率,降低了运行时间。     

An analytical algorithm for generalized low-rank approximations of matrices

The algorithm for generalized low-rank approximations of matrices (GLRAM) has been developed recently. In this paper, the optimality property of GLRAM is revealed. Accordingly, an analytical method for GLRAM is proposed. The proposed method is non-iterative. Moreover, the relationship between 2DPCA and GLRAM is shown.     

天基监视雷达

介绍了天基雷达的三种类型：第一种交会雷达、第二种遥感卫星上的合成孔径雷达(SAR)成像雷达、第三种天基监视雷达，该雷达目前正在大力开发。重点讨论对天基监视雷达的设计要求和具体设计技术。