基于切割子模块的单样本人脸识别

针对单样本人脸识别问题,本文提出了一种基于单样本切割的子模块主成分分析方法.该方法将单样本人脸图片切割成大小相同、互不重叠的多个子模块,切割后的子模块集构成新的样本集.对所有子模块作主成分分析(PCA)并提取特征,同一人脸的子模块特征系数作为分类识别的依据.在ORL人脸库上的测试结果表明,同PCA,(PC)2A,Sub-pattern LDA相比,该方法具有更好的识别率.     

基于独立成分分析的掌纹识别

本文研究了独立成分分析(ICA)两种不同的结构ICA I和ICAII在掌纹识别中的应用.为了提高识别准确性和可靠性,该方法首先对掌纹图像进行预处理,提取掌纹感兴趣(ROI)区域进行特征提取和匹配.为了减少计算量,运用ICA算法之前,先采用主成分分析(PCA)算法去除掌纹图像的二阶统计特征相关性,其余的高阶统计特征由ICA分离.对于PolyU掌纹图像库,基于ICA模型的预测误差平方和(SPE)小于PCA,而且重构的原始图像优于PCA.为了比较两种算法识别性能,本丈分别用PCA、ICA I、ICAII提取特征掌纹子空间,然后将待识别图像投影到低维子空间上,最后用余弦距离进行掌纹匹配.实验结果表明,ICA算法两种结构的识别率均高于PCA,ICAII在性能上优于ICA I.     

基于样本协方差矩阵谱分离特性的波达方向估计方法

小快拍条件下利用样本协方差矩阵代替统计协方差矩阵会带来较大误差,导致传统DOA估计算法不能准确估计目标方位。通过分析发现在不同阵元数与快拍数之比情况下,不管相干源还是独立源,样本协方差矩阵都具有明显的谱分离特性,在此基础上提出了采用小快拍的主特征空间目标波达方向估计方法,该方法利用导向向量与噪声子空间正交,且与信号子空间平行的特性,使用导向向量与主特征空间相乘再取反余弦构造出目标DOA估计幅度。仿真与水池实验中阵元数与样本数之比为1时依然可以准确将多个目标分辨出;海试数据验证中,阵元数与样本数之比也同样为1时,两个相邻目标可以正确分辨,而MUSIC算法则有伪目标出现。     

一种基于自样本学习的人脸图像超分辨率复原算法

针对人脸图像超分辨率复原问题,提出了一种新的基于自样本学习的超分辨率复原算法.该算法从输入图像本身提取训练样本库,并采用矢量量化的方法对训练样本进行分类.再利用并行设计的多类预测器对每类样本进行学习训练,指导高频信息的估计重建.对来自输入图像本身的自样本训练集合和来自特定训练图像库的特定训练样本集合进行了对比研究.实验结果表明提出算法在图像重建质量和实现速度上都有很好的表现.     

基于Gabor小波的人脸表情识别

提出通过提取人脸表情图像的Gabor特征,结合二次降维的方法,进行人脸表情识别.针对Gabor特征提取后维数变高,冗余很大的特点,先对高维特征进行采样,再引入二维PCA算法对Gabor特征进行选择,以达到降维的目的.然后采用基于模糊积分的多分类器联合的方法对7种表情进行融合识别.在JAFFE库上进行测试的结果验证了该算法的有效性,与2DPCA算法及传统特征提取算法相比,本文算法取得了较高的识别速度和精确度.该算法能更有效的提取反映表情状态的特征.     

PCA与SVD信号处理效果相似性与机理分析

将主成分分析(Principal Component Analysis,PCA)用于信号处理,并与奇异值分解(Singular Value Decomposition,SVD)方法比较。分析总结PCA及SVD信号处理原理,提出基于PCA的特征值差分谱理论用于信号消噪。结果表明,PCA与SVD的处理效果较相似,相似性原因为原始矩阵右奇异向量即为协方差矩阵特征向量。SVD较PCA的重构误差小,因SVD无需计算协方差矩阵,可避免舍入误差产生。     

分块PCA在脸像识别中的应用

鉴于整幅人脸图像主成分提取(PCA)特征脸算法的高计算复杂度,本文提出了基于分块PCA的脸像识别算法,先对每幅脸像等分成相同的块,再对各子块图像预处理,采用像素均值法的降采样和能量归一化处理以降低维数和消除光照的影响,再合并成一个向量,将预处理得到的向量进行PCA降维,最后采用k-近邻分类器进行分类识别。在Yale人脸库中实验结果表明该方法的有效性。     

基于三维模型的多姿态人脸识别

提出了一种利用三维人脸模型匹配二维人脸图像的分层人脸识别方法和基于模糊数学的人脸姿态角度估计算法.对多姿态二维图像进行姿态空间划分,利用主成分分析方法(PCA)形成多姿态特征脸.识别过程首先估计测试图像姿态和模糊姿态角,在估计的姿态空间内采用基于PCA的方法进行第一层识别得到候选个体,然后利用候选个体的三维模型结合模糊姿态角产生虚拟图像,利用相关进行第二层识别.实验结果表明,该方法对姿态的变化有较好的鲁棒性.     

基于独立成分分析的掌纹识别

本文研究了独立成分分析（ICA）两种不同的结构ICAⅠ和ICAⅡ在掌纹识别中的应用。为了提高识别准确性和可靠性,该方法首先对掌纹图像进行预处理,提取掌纹感兴趣（ROI）区域进行特征提取和匹配。为了减少计算量,运用ICA算法之前．先采用主成分分析（PCA）算法去除掌纹图像的二阶统计特征相关性,其余的高阶统计特征由ICA分离。对于PolyU掌纹图像库,基于ICA模型的预测误差平方和（SPE）小于PCA,而且重构的原始图像优于PCA。为了比较两种算法识别性能,本文分别用PCA、ICAⅠ、ICAⅡ提取特征掌纹子空间,然后将待识别图像投影到低维子空间上,最后用余弦距离进行掌纹匹配。实验结果表明,ICA算法两种结构的识别率均高于PCA,ICAⅡ在性能上优于ICAⅠ。     

基于混沌理论和支持向量机的人脸识别方法

针对如何选定主成分分析(PCA)特征维数和如何选定支持向量机(SVM)的参数来进一步提高人脸识别系统性能的问题,提出了一种基于混沌理论和支持向量机的人脸识别方法.首先,在统一的目标函数下,在采用PCA方法对人脸图像进行降维和将得到的特征送入SVM中进行训练期间,使用具有可操作性的改进混沌优化算法同时对PCA图像特征维数和分类器参数进行优化选择,然后用得到的优化人脸特征和最佳参数的分类器对未知图像进行识别.基于该方法,对ORL和Yale人脸库进行实验,其识别率都高达99%以上,仿真结果表明,该方法极大地提高了人脸识别能力.     

Cross‐band fusion by energy weight as solution to illumination and arch restrictions in palm‐print recognition

Palm‐print image is often influenced by illumination and the arch of the palm‐print results in a great deal of noise during the course of palm‐print image acquisition. This article presents palm‐print recognition based on cross‐band fusion by energy weight and comprehensively takes into account the noisy properties of various sub‐bands in single wavelet level and decomposition coefficient of the adjacent sub‐band, thus the method of energy weight based on palm‐print image is employed. Then two‐dimensional principal component analysis (2DPCA) is employed for dimension reduction and decorrelated. Finally, a nearest neighbor classifier is used for palm‐print recognition. Experimental results on Hong Kong PolyU palm‐print database show that correct recognition rate can reach 100% by the method presented within this article. Correct recognition rate and recognition efficiency is higher than that of 2DPCA and WT + DCT + 2DPCA (Wavelet Transform, Discrete Cosine Transform and 2DPCA, WT + DCT + 2DPCA). © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 350–355, 2009     

Maximum likelihood principal component analysis with correlated measurement errors: theoretical and practical considerations

Procedures to compensate for correlated measurement errors in multivariate data analysis are described. These procedures are based on the method of maximum likelihood principal component analysis (MLPCA), previously described in the literature. MLPCA is a decomposition method similar to conventional PCA, but it takes into account measurement uncertainty in the decomposition process, placing less emphasis on measurements with large variance. Although the original MLPCA algorithm can accommodate correlated measurement errors, two drawbacks have limited its practical utility in these cases: (1) an inability to handle rank deficient error covariance matrices, and (2) demanding memory and computational requirements. This paper describes two simplifications to the original algorithm that apply when errors are correlated only within the rows of a data matrix and when all of these row covariance matrices are equal. Simulated and experimental data for three-component mixtures are used to test the new methods. It was found that inclusion of error covariance information via MLPCA always gave results which were at least as good and normally better than PCA when the true error covariance matrix was available. However, when the error covariance matrix is estimated from replicates, the relative performance depends on the quality of the estimate and the degree of correlation. For experimental data consisting of mixtures of cobalt, chromium and nickel ions, maximum likelihood principal components regression showed an improvement of up to 50% in the cross-validation error when error covariance information was included.     

Motion estimation in wide band synthetic aperture sonar based on the raw echo data using the method of displaced phase center antenna

Phase errors in synthetic aperture sonar (SAS) imaging must be reduced to less than one eighth of a wavelength so as to avoid image destruction. Most of the phase errors occur as a result of platform motion errors, for example, sway yaw and surge that are the most important error sources. The phase error of a wide band synthetic aperture sonar is modeled and solutions to sway yaw and surge motion estimation based on the raw sonar echo data with a Displaced Phase Center Antenna (DPCA) method are proposed and their implementations are detailed in this paper. It is shown that the sway estimates can be obtained from the correlation lag and phase difference between the returns at coincident phase centers. An estimate of yaw is also possible if such a technique is applied to more than one overlapping phase center positions. Surge estimates can be obtained by identifying pairs of phase centers with a maximum correlation coefficient. The method works only if the platform velocity is low enough such that a number of phase centers from adjacent pings overlap.     

基于2DPCA的矩阵时间序列统计监控及推断

在多元统计过程控制的研究中,越来越多的学者开始关注到矩阵数据的在线监控问题。矩阵数据通常可被拉直为向量数据再进行监控,但拉直操作破坏了矩阵数据的原有结构信息。而2DPCA方法直接对矩阵数据进行特征提取,可保留矩阵的结构特征。因此,利用2DPCA方法研究矩阵值时间序列的统计监控及推断是有意义的。首先基于2DPCA方法对矩阵数据进行正交投影获取特征,通过融合这些特征构造监控统计量;其次证明了该监控统计量的极限分布为卡方分布,并利用该分布进行统计推断。模拟实验表明：该方法理论正确;当样本容量较大时,该方法相对于同类方法表现更优。     

基于互信息的主成分分析用于声场景分类

主成分分析是声场景分类中常用的特征选择方法。针对主成分分析的局限性,提出一种基于互信息的主成分分析方法。这一方法引入类别信息,用不同声场景条件下特征之间的互信息矩阵之和替代传统主成分分析中的协方差矩阵,计算其特征向量与特征值,特征向量表示由原始特征空间向新的主成分空间的转换系数,特征值则用于计算主成分的累计贡献率并判断主成分维数。声场景分类实验结果表明,该方法较之传统主成分分析方法降维效果更好,辅以神经网络分类器,计算得到的分类正确率更高。     

不同算法模型对光谱重构精度的影响

目的研究光谱颜色复制中原稿图像的光谱信息,并对目标色的光谱反射率进行重构,探究影响重构光谱精度的因素。方法通过选取Munsell Color Matt(1269色块)和Color Checker Classic(24色块)2种色卡作为光谱反射率数据样本,建立不同的主成分分析线性重构模型,选取不同的基向量个数分别重构光谱,并对其精度进行评价,取Classic色卡模拟多光谱图像中重建光谱反射率的目标色,研究比较光谱重构模型和基向量数目对重构精度的影响。结果实验表明,降维模型1最终恢复的数据在RMSE,GFC和色差上均优于模型2,随着基向量数目的增加,2种降维模型差距在减小,当基向量数目达到13以后,2种模型基本没差异。结论文中提到光谱重建模型1和7个基向量是重构光谱图像的最佳方案。     

Conjugate image points by an adaptive estimator for the gray‐level variance

Abstract

A least‐squares image matching algorithm was extended to adjust the different possible variances, auto‐ and cross‐covariances found in a gray‐level covariance matrix. Scaling variance and covariance components were estimated iteratively, based on some positive‐semidefinite accompanying matrices. The theory of a best linear, unbiased estimator for the scale factors has been presented in detail. Conjugate‐point accuracy results were obtained from 114 pairs of Radarsat‐1 crossroads and pond‐corner image windows. A 14% improvement in sub‐pixel matching accuracy was achieved by adhering to the proposed BLU‐Estimating algorithm, in particular for a category of the 11×11 image‐window size.     

Interpretation of static time-of-flight secondary ion mass spectra of adsorbed protein films by multivariate pattern recognition

Multivariate analysis has become increasingly common in the analysis of multidimensional spectral data. We previously showed that the multivariate analysis technique principal component analysis (PCA) is an excellent method for interpreting the static time-of-flight secondary ion mass spectrometry (TOF-SIMS) spectra of adsorbed protein films. PCA is an unsupervised pattern recognition technique that loses resolution between spectra of different proteins as more proteins are added to the data set due to large within-group variation. The supervised pattern recognition techniques discriminant principal component analysis (DPCA) and linear discriminant analysis (LDA), which aim to control within-group variation while maximizing between-group separation to enhance discrimination between groups, were compared with PCA using data sets of TOF-SIMS spectra of proteins adsorbed onto mica and PTFE substrates. DPCA and LDA quantitatively improved discrimination between groups and provided different information about the data than PCA. LDA was able to classify unknown samples with a misclassification rate lower than PCA or DPCA. Both unsupervised and supervised pattern recognition techniques are useful for the interpretation and classification of static TOF-SIMS spectra of adsorbed protein films.     

多权值电容归一化方法的研究

基于并联模型且考虑了不同介质满场分布时电容值对测量电容值的影响,提出了一种多权值电容归一化方法,所建模型不仅适用于两相流还适用于两相流以上的多相流。实验结果表明:在包含2种以上介质的多相流图像重建中,使用多权值模型的图像重建精度的均方差为0.0044,明显优于并联模型的0.0322,因此,多权值模型能够提高图像重建算法精度。分析重建图像发现,该模型还能提高物场中心处的灵敏度,使得物场中心处物体的成像误差减小,从而提高重建图像质量。