基于稀疏表示的高噪声人脸识别及算法优化

doi:10.3724/SP.J.1087.2012.02313

计算机应用 ›› 2012, Vol. 32 ›› Issue (08): 2313-2319.DOI: 10.3724/SP.J.1087.2012.02313

基于稀疏表示的高噪声人脸识别及算法优化

蔡体健¹,²,樊晓平³,⁴,刘遵雄¹

1. 华东交通大学信息工程学院，南昌 330013
2. 中南大学信息科学与工程学院，长沙 410075
3. 中南大学信息科学与工程学院，长沙 410083
4. 湖南财政经济学院网络化系统研究所，长沙 410205

收稿日期:2012-01-11 修回日期:2012-03-03 发布日期:2012-08-28 出版日期:2012-08-01
通讯作者: 蔡体健
作者简介:蔡体健(1968-),女,湖南长沙人,副教授,博士，主要研究方向：压缩感知、图像处理;
樊晓平(1961-)，男，浙江绍兴人，教授，博士生导师，博士，主要研究方向：无线传感器网络、智能信息处理、系统与控制;
刘遵雄(1967-)，男，江西瑞昌人，教授，博士，主要研究方向：机器学习、数据挖掘。
基金资助:
国家自然科学基金资助项目(60870010，61065003)

Dense noise face recognition based on sparse representation and algorithm optimization

CAI Ti-jian¹,²,FAN Xiao-ping³,⁴,LIU Jun-xiong¹

1. School of Information Engineering, East China Jiaotong University, Nanchang Jiangxi 330013, China
2. School of Information Science and Engineering, Central South University, Changsha Hunan 410075, China
3. School of Information Science and Engineering，Central South University, Changsha Hunan 410083,China
4. Institute of Networked Systems, Hunan University of Finance and Economics, Changsha Hunan 410205, China

Received:2012-01-11 Revised:2012-03-03 Online:2012-08-28 Published:2012-08-01
Contact: CAI Ti-jian

摘要/Abstract

摘要： 为提高基于稀疏表示人脸识别的速度和抗噪性能，研究了交叉花束(CAB)模型及压缩感知重构算法。针对重构算法中的大矩阵求逆，提出快速正交匹配追踪(FOMP)算法，可将运算量较高的矩阵求逆运算转变为轻量级向量矩阵运算。为增加高噪声图片的有效信息量，提出几种实用且有效的方法，并通过实验验证这些方法都能提高高噪声人脸识别率，可识别的噪声比例提高到75%，具有一定的实用价值。

关键词: 压缩感知, 稀疏表示, 人脸识别, 贪婪匹配追踪算法, 过完备字典

Abstract: To improve the speed and anti-noise performance of face recognition based on sparse representation, the Cross-And-Bouquet (CAB) model and Compressed Sensing (CS) reconstruction algorithm were studied. Concerning the large matrix inversion of reconstruction algorithm, a Fast Orthogonal Matching Pursuit (FOMP) algorithm was proposed. The proposed algorithm could convert the high complexity operations of matrix inversion into the lightweight operation of vector-matrix computation. To increase the amount of effective information in dense noise pictures, several practical and efficient methods were put forward. The experimental results verify that these methods can effectively improve the face recognition rate in dense noise cases, and identifiable noise ratio can reach up to 75%. These methods are of practical values.

Key words: Compressed Sensing (CS), sparse representation, face recognition, Orthogonal Matching Pursuit (OMP) algorithm, overcomplete dictionary

中图分类号:

TP391.4

蔡体健樊晓平刘遵雄. 基于稀疏表示的高噪声人脸识别及算法优化[J]. 计算机应用, 2012, 32(08): 2313-2319.

CAI Ti-jian FAN Xiao-ping LIU Jun-xiong. Dense noise face recognition based on sparse representation and algorithm optimization[J]. Journal of Computer Applications, 2012, 32(08): 2313-2319.

参考文献

[1]戴琼海,付长军,季向阳. 压缩感知研究[J].计算机学报,2011, 34(3): 425-434. [2]李树涛,魏丹. 压缩传感综述[J].自动化学报,2009, 35(11): 1369-1377. [3]石光明,刘丹华,高大化,等.压缩感知理论及其研究进展[J].电子学报,2009,37(5):1070-1081. [4]YANG A Y, ZHOU Z, MA Y, et al. Towards a robust face recognition system using compressive sensing [C]// Proceedings of Interspeech: 11th Annual Conference of the International Speech Communication Association. Makuhari, Chiba: [s.n.], 2010: 2250-2253. [5]WRIGHT J, GANESH A, YANG A Y, et al. Robust face recognition via sparse representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227. [6]TROPP J A, GILBERT A C. Signal recovery from random measurements via orthogonal matching pursuit [J].IEEE Transactions on Information Theory, 2007, 53(12): 4655-4665. [7]SHA W.Orthogonal matching pursuit algorithm for compressive sensing ［CP/OL］．［2011-09-01］. http://www.eee.hku.hk/~wsha/Freecode/freecode.htm. [8]KARABULUT G Z,MOURA L,PANARIO D,et al. Flexible tree- search based orthogonal matching pursuit algorithm[C]// ICASSP '05: IEEE International Conference on Acoustics, Speech, and Signal Processing. Piscataway: IEEE, 2005:673-676. [9]NEEDELL D, VERSHYNIN R. Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit [J].IEEE Journal of Selected Topics in Signal Processing, 2010, 4(2): 310-316. [10]刘亚新,赵瑞珍,胡绍海,等.用于压缩感知信号重建的正则化自适应匹配追踪算法[J].电子与信息学报,2010,32(11):2713-2717. [11]DO T T, GAN L, NGUYEN N, et al. Sparsity adaptive matching pursuit algorithm for practical compressed sensing [C]// 42nd Asilomar Conference on Signals, Systems and Computers. Piscataway: IEEE, 2008:581-587. [12]MO QUN, SHEN YI. Remark on the restricted isometry property in orthogonal matching pursuit[EB/OL]. ［2012-01-18］. http://www.paper.edu.cn/index.php/default/en_releasepaper/content/4408549. [13]MALEH R. Improved RIP analysis of orthogonal matching pursuit[EB/OL].［2012-01-18］. http://arxiv.org/abs/1102.4311. [14]杨荣根,任明武,杨静宇. 基于稀疏表示的人脸识别方法[J].计算机科学,2010,37(9):267-270. [15]CANDES E J, TAO T. Decoding by linear programming[J].IEEE Transactions on Information Theory, 2005,51(12): 4203-4215. [16]WRIGHT J,MA Y.Dense error correction via l1-minimization [C]// ICASSP 2009:IEEE International Conference on Acoustics, Speech and Signal Processing, 2009:3033-3036. [17]邓承志.图像的稀疏表示及其应用研究[D].武汉：华中科技大学,2008. [18]GEORGHIADES A S,BELHUMEUR P N,KRIEGMAN D J.From few to many: Illumination cone models for face recognition under variable lighting and pose [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(6): 643-660. [19]方红,杨海蓉. 贪婪算法与压缩感知理论[J].自动化学报,2011,37(12):1413-1421.

基于稀疏表示的高噪声人脸识别及算法优化

Dense noise face recognition based on sparse representation and algorithm optimization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	高工, 杨红雨, 刘洪. 基于深度学习的三维点云人脸识别[J]. 计算机应用, 2021, 41(9): 2736-2740.
[2]	裴春阳, 樊宽刚, 马政. 基于边缘保留分解和改进稀疏表示的医学图像融合[J]. 计算机应用, 2021, 41(7): 2092-2099.
[3]	任晓奎, 刘鹏飞, 陶志勇, 刘影, 白立春. 基于单快拍信号到达角估计算法的室内入侵检测[J]. 计算机应用, 2021, 41(4): 1153-1159.
[4]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[5]	沈子懿, 王卫亚, 蒋东华, 荣宪伟. 基于Hopfield混沌神经网络和压缩感知的可视化图像加密算法[J]. 计算机应用, 2021, 41(10): 2893-2899.
[6]	王丽娟, 陈少敏, 尹明, 许跃颖, 郝志峰, 蔡瑞初, 温雯. 基于近邻图改进的块对角子空间聚类算法[J]. 计算机应用, 2021, 41(1): 36-42.
[7]	赵青, 余元辉. 基于分层特征化网络的三维人脸识别[J]. 计算机应用, 2020, 40(9): 2514-2518.
[8]	方书雅, 刘守印. 基于学生人体检测的无感知课堂考勤方法[J]. 计算机应用, 2020, 40(9): 2519-2524.
[9]	席雅睿, 乔志伟, 温静, 张艳娇, 杨雯晶, 闫慧文. 基于Chambolle-Pock算法框架的高阶TV图像重建算法[J]. 计算机应用, 2020, 40(6): 1793-1798.
[10]	徐志强, 蒋铁钢, 杨立波. 基于随机支撑挑选的广义正交匹配追踪算法[J]. 计算机应用, 2020, 40(4): 1104-1108.
[11]	杨立波, 蒋铁钢, 徐志强. 基于混合梯度的硬阈值追踪算法[J]. 计算机应用, 2020, 40(3): 912-916.
[12]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[13]	龚锐, 丁胜, 章超华, 苏浩. 基于深度学习的轻量级和多姿态人脸识别方法[J]. 计算机应用, 2020, 40(3): 704-709.
[14]	高彦彦, 李莉, 张晶, 贾英茜. 结合梯度投影稀疏重构和复数小波的图像重构[J]. 计算机应用, 2020, 40(2): 486-490.
[15]	陈放, 刘晓瑞, 杨明业. 基于活体检测和身份认证的人脸识别安防系统[J]. 计算机应用, 2020, 40(12): 3666-3672.