Face recognition of generalized parallel two-dimensional complex discriminant analysis

Wanjun Liu; Xiaohuan Bing; Wentao Jiang; Shengchong Zhang

doi:10.11834/jig.170671

Image Analysis and Recognition | Views : 0 下载量: 5 CSCD: 1

PDF
Export
Share
Collection
Album

Face recognition of generalized parallel two-dimensional complex discriminant analysis
Vol. 23, Issue 9, Pages: 1359-1370(2018)
Received：03 January 2018，

Revised：2018-3-12，

Published：16 September 2018
DOI： 10.11834/jig.170671
稿件说明：

移动端阅览

DOI：

Wanjun Liu, Xiaohuan Bing, Wentao Jiang, Shengchong Zhang. Face recognition of generalized parallel two-dimensional complex discriminant analysis[J]. Journal of Image and Graphics, 2018, 23(9): 1359-1370. DOI： 10.11834/jig.170671.

摘要

目的

针对2维线性鉴别分析提取人脸特征向量稳定性较差、仅对行或列方向提取特征时容易丢失不同行或列间有助于鉴别分析的协方差信息、同时存在特征维数较高的问题，提出一种广义并行2维复判别分析的人脸识别方法。

方法

首先对人脸图像进行广义并行2维线性判别分析处理，根据特征值贡献率动态选取特征向量组成正交投影矩阵，完成水平和垂直方向上的投影；其次将处理后得到的两类特征矩阵以复数的实部和虚部形式相加，对融合后的特征矩阵进行广义2维复判别分析处理得到复特征矩阵；然后以复特征矩阵的特征值大小来衡量特征矩阵分量的识别性能，对特征矩阵分量进行重新排序，选取最具鉴别力的分量形成最终表征人脸的特征；最后采用最大相似度分类器比较测试样本与训练样本特征的相似度，进行人脸图像特征的分类识别。

结果

在Yale、ORL、FERET、CMU-PIE及LFW人脸数据库上进行实验测试，该方法的最优识别率分别为100%、100%、98.98%、99.76%及98.67%，特征维数在85~90之间，表明该方法对复杂条件下的人脸识别有较高的准确率和较低的空间占有率。

结论

该方法能够有效克服2维线性鉴别分析提取特征稳定性差、特征空间中特征重叠、存储系数多、特征维数高的缺点，表现出较高鲁棒性和准确率及较低空间复杂度的特性。

Abstract

Objective

A face recognition approach of generalized parallel two-dimensional (2D) complex discriminant analysis was proposed to tackle such problems that 2D linear discriminant analysis demonstrated poor stability when extracting facial feature vectors

the covariance information of different rows or columns which was conducive to discriminant analysis was very likely to get lost when only features in rows or columns were being extracted

and the dimensions where features existed were relatively high.

Method

Firstly

generalized parallel 2D linear discriminant analysis was conducted on facial images

and the feature vectors are selected according to the feature value contribution rate to form the orthogonal projection matrix

then the projection of horizontal and vertical direction is completed; secondly

the two types of feature matrices obtained after processing were added together in forms of real part and imaginary part of complex numbers

and the complex feature matrices were obtained by conducting generalized 2D complex discriminant analysis on feature matrices having been fused; then

the recognition performance of feature matrix components was measured based on feature values of complex feature matrices

the feature matrix components were re-ranked

and the most discriminative components were selected to form the final features characterizing human faces; and at last

maximum similarity classifier was used to classify and recognize features of human face images by comparing the similarity between the test samples and the training sample features.

Result

Yale

ORL

FERET

CMU-PIE and LFW face databases were experimented

from which the optimal recognition rates obtained by using this method were respectively 100%

100%

98.98%

99.76%

and 98.67%

with the feature dimensions ranging from 85 to 90

which indicated that this method delivered relatively high face recognition precision and low space occupancy in complex conditions.

Conclusion

This method could effectively overcome drawbacks such as poor feature extraction stability of 2D linear discriminant analysis

overlap of features in feature space

excessive storage coefficients

and high dimension of features

manifesting high robustness

great precision

and low space complexity.

关键词

Keywords

references

Chan C H, Kittler J, Tahir M A. Kernel fusion of multiple histogram descriptors for robust face recognition[M]//Hancock E R, Wilson R C, Windeatt T, et al. Structural, Syntactic, and Statistical Pattern Recognition. Berlin, Heidelberg:Springer, 2017: 718-727. [ DOI: 10.1007/978-3-642-14980-1_71 http://dx.doi.org/10.1007/978-3-642-14980-1_71 ]

Yin X, Liu X M. Multi-task convolutional neural network for pose-invariant face recognition[J]. IEEE Transactions on Image Processing, 2018, 27(2):964-975.[DOI:10.1109/TIP.2017.2765830]

Li Q Y, Jiang J G, Qi M B. Face recognition algorithm based on improved deep networks[J]. Acta Electronica Sinica, 2017, 45(3):619-625.

李倩玉, 蒋建国, 齐美彬.基于改进深层网络的人脸识别算法[J].电子学报, 2017, 45(3):619-625. [DOI:10.3969/j.issn.0372-2112.2017.03.017]

Yuan H, Wang Z H, Jiang W T. 3D Face recognition approach based on singular point neighborhood structure[J]. Control and Decision, 2017, 32(10):1739-1748.

袁姮, 王志宏, 姜文涛.基于奇异点邻域结构的三维人脸识别方法[J].控制与决策, 2017, 32(10):1739-1748. [DOI:10.13195/j.kzyjc.2016.0936]

Kong R, Zhang B. Research on face recognition method under uncontrolled illumination variation[J]. Journal of System Simulation, 2016, 28(3):689-695.

孔锐, 张冰.光照变化条件下人脸识别方法研究[J].系统仿真学报, 2016, 28(3):689-695.

Gan J Y, He G H, He S B. Kernel null space linear discriminant analysis and its applications in face recognition[J]. Chinese Journal of Computers, 2014, 37(11):2374-2379.

甘俊英, 何国辉, 何思斌.核零空间线性鉴别分析及其在人脸识别中的应用[J].计算机学报, 2014, 37(11):2374-2379. [DOI:10.3724/SP.J.1016.2014.02374]

Fu J P, Chen X H, Ge X Q. Face recognition by generalized kernel discriminant analysis via L 2, 1 -norm regularization[J]. Journal of Frontiers of Computer Science and Technology, 2017, 11(1):124-133..

傅俊鹏, 陈秀宏, 葛骁倩. L 2, 1 范数正则化的广义核判别分析及其人脸识别[J].计算机科学与探索, 2017, 11(1):124-133. [DOI:10.3778/j.issn.1673-9418.1510052] .

Ruan Y, Chen H W, Liu Z H, et al. Quantum principal component analysis algorithm[J]. Chinese Journal of Computers, 2014, 37(3):666-676.

阮越, 陈汉武, 刘志昊, 等.量子主成分分析算法[J].计算机学报, 2014, 37(3):666-676. [DOI; 10.3724/SP.J.1016.2014.00666]

Muqeet M A, Holambe R S. Face recognition using LDA based generalized half band polynomial wavelet filter bank[C]//International Conference on Electrical, Electronics, and Optimization Techniques. Chennai, India: IEEE, 2016: 4649-4653. [ DOI: 10.1109/ICEEOT.2016.7755601 http://dx.doi.org/10.1109/ICEEOT.2016.7755601 ]

Juneja K. A noise robust VDD composed PCA-LDA model for face recognition[C]//Proceedings of the 2nd International Conference on Information, Communication and Computing Technology. Singapore: Springer, 2017: 216-229. [ DOI: 10.1007/978-981-10-6544-6_21 http://dx.doi.org/10.1007/978-981-10-6544-6_21 ]

Hu Z P, He W, Wang M, et al. Multi-level deep network fused for face recognition[J]. Pattern Recognition and Artificial Intelligence, 2017, 30(5):448-455.

胡正平, 何薇, 王蒙, 等.多层次深度网络融合人脸识别算法[J].模式识别与人工智能, 2017, 30(5):448-455. [DOI:10.16451/j.cnki.issn1003-6059.201705007]

Kong H, Wang L, Teoh E K, et al. A framework of 2D fisher discriminant analysis: application to face recognition with small number of training samples[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). San Diego, CA, USA: IEEE, 2005. [ DOI: 10.1109/CVPR.2005.30 http://dx.doi.org/10.1109/CVPR.2005.30 ]

Wu H P, Dai S K. Face recognition of 2DLDA based on ULBP eigensubspace[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(10):894-899.

吴煌鹏, 戴声奎.基于ULBP特征子空间的2DLDA人脸识别方法[J].模式识别与人工智能, 2014, 27(10):894-899.[DOI:10.3969/j.issn.1003-6059.2014.10.005]

Yin J, Sun S L. Two dimensional discriminative projection based on nearest orthogonal matrix and its application to face recognition[J]. Journal of Computer-Aided Design&Computer Graphics, 2017, 29(8):1457-1464.

殷俊, 孙仕亮.基于最近正交矩阵的二维鉴别投影及人脸识别应用[J].计算机辅助设计与图形学学报, 2017, 29(8):1457-1464.

Noushath S, Hemantha Kumar G, Shivakumara P. (2D) 2 LDA:an efficient approach for face recognition[J]. Pattern Recognition, 2006, 39(7):1396-1400.

Hu X, Yu W X, Yu Q. Study on face recognition based on two-dimensional combined complex discriminant analysis[J]. Computer Engineering and Design, 2010, 31(11):2514-2518.

胡晓, 俞王新, 余群.基于二维复判别分析的人脸识别研究[J].计算机工程与设计, 2010, 31(11):2514-2518.

Song J D, Zhou M Q, Lu J H, et al. A novel method based on generalized 2DLDA for application of face recognition[J]. Journal of Chinese Computer Systems, 2015, 36(4):856-861.

宋家东, 周明全, 卢金环, 等.一种基于广义2DLDA算法在人脸识别的应用[J].小型微型计算机系统, 2015, 36(4):856-861.

Zhang X H, Shan S G, Cao B, et al. CAS-PEAL:a large-scale Chinese face database and some primary evaluation[J]. Journal of Computer-Aided Design&Computer Graphics, 2005, 17(1):9-17.

张晓华, 山世光, 曹波, 等. CAS-PEAL大规模中国人脸图像数据库及其基本评测介绍[J].计算机辅助设计与图形学学报, 2005, 17(1):9-17.[DOI:10.3321/j.issn:1003-9775.2005.01.002]

Sim T, Baker S, Bsat M. The CMU pose, illumination, and expression database[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12):1615-1618.[DOI:10.1109/TPAMI.2003.1251154]

Phillips P J, Moon H, Rizvi S A, et al. The FERET evaluation methodology for face-recognition algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10):1090-1104.[DOI:10.1109/34.879790]

Huang G B, Ramesh M, Berg T, et al. Labeled faces in the wild: a database for studying face recognition in unconstrained environments[R]. Massachusetts: University of Massachusetts, 2007.

Alert me when the article has been cited

提交

Human facial texture and fore-background differences-relevant anti-spoofing detection

Mask-fused human face image quality assessment method

Review on face liveness detection

Face recognition with superposed linear sparse representation based on discriminative nonconvex low-rank matrix decomposition

Jointly using convolutional neural network and PCA-constrained optimization model for sparse representation-based classification