[1]唐 娴,黄军伟.低秩鲁棒性主成分分析的遮挡人脸识别[J].南京理工大学学报(自然科学版),2017,41(04):460.[doi:10.14177/j.cnki.32-1397n.2017.41.04.010]
 Tang Xian,Huang Junwei.Occlusion face recognition based on robust principal component analysis and low rank[J].Journal of Nanjing University of Science and Technology,2017,41(04):460.[doi:10.14177/j.cnki.32-1397n.2017.41.04.010]
点击复制

低秩鲁棒性主成分分析的遮挡人脸识别()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年04期
页码:
460
栏目:
出版日期:
2017-08-31

文章信息/Info

Title:
Occlusion face recognition based on robust principal component analysis and low rank
文章编号:
1005-9830(2017)04-0460-06
作者:
唐 娴黄军伟
商丘学院 计算机工程学院,河南 商丘 476000
Author(s):
Tang XianHuang Junwei
Department of Cmputer Engineering,Shangqiu University,Shangqiu 476000,China
关键词:
鲁棒性主成分分析 模式识别 遮挡人脸 低秩映射 误识率
Keywords:
robust principal component analysis pattern recognition occlusion face low rank mapping error rate
分类号:
TP391.4
DOI:
10.14177/j.cnki.32-1397n.2017.41.04.010
摘要:
为了提高遮挡人脸的识别效果,提出了低秩鲁棒性主成分分析的遮挡人脸识别算法。首先采集人脸图像,并进行相应的预处理,然后采用鲁棒性主成分分析对人脸样本进行分解,并建立人脸图像训练样本和测试样本的低秩矩阵和误差矩阵,最后根据误差矩阵对人脸识别进行加权和识别,并采用经典人脸数据库进行仿真实验,结果表明,低秩鲁棒性主成分分析的遮挡人脸识别率得到显著提高,降低了遮挡人脸的误识率,具有更优的鲁棒性。
Abstract:
In order to improve the recognition accuracy of occlusion face,a novel occlusion face recognition algorithm combining robust principal component analysis and low rank is proposed.Firstly,face images are collected and are correspondingly pretreated,and secondly the face samples are decomposed by using robust principal component analysis to obtain low rank data matrix and sparse error matrix,and face images of training samples and testing samples are established.At last face is weighted and recognized according to the error matrix,the classic face database is used to carried out simulation experiment.The results show that the proposed algorithm has improved the occluded face recognition accuracy significantly,effectively reduces the error rate of the occluded face,and has better robustness.

参考文献/References:

[1] 杨章静,刘传才,顾兴健,等.依概率分类的保持投影及其在人脸识别中的应用[J].南京理工大学学报,2013,37(1):7-11.
Yang Zhangjing,Liu Chuancai,Gu Xingjian,et al.Probabilistic classification preserving projections and its application to face recognition[J].Journal of Nanjing University of Science and Technology,2013,37(1):7-11.
[2]Naseem I,Togneri R,Bennamoun M.Linear regression for face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(11):2106-2112.
[3]Kim Jong Kyoung,Choi Seungjin.Probabilistic models for semi-supervised discriminative motif discovery in DNA sequences[J].IEEE-ACM Transactions on Computational Biology and Bioinformatics,2011,8(5):1309-1324.
[4]Kavitha T,Cuntai G,Tong L C,et al.Adaptive tracking of discriminative frequency components in electroencephalograms for a robust brain-computer interface[J].Journal of Neural Engineering,2011,8(3):36007-36019.
[5]李根,李文辉.基于思维进化的机器学习的遮挡人脸识别[J].吉林大学学报(工学版),2013,35(1):171-184.
Li Gen,Li Wenhui.Face occlusion recognition based on MEBML[J].Journal of Jilin University(Engineering and Technology Edition),2013,35(1):171-184.
[6]邱立达,傅平,林南,等.具有判别能力的低秩映射字典对学习[J].激光与光电子学进展,2016,53(7):31-38.
Qiu Lida,Fu Ping,Lin Nan,et al.Discriminative low-rank projection dictionary pair learning[J].Laser & Optoelectronics Progress,2016,53(7):31-38.
[7]翟彭奎,甘俊英,李景文.基于彩色信息融合和同伦算法的遮挡鲁棒人脸识别方法研究[J].信号处理,2011,27(11):1762-1767.
Zhai Pengkui,Gan Junying,Li Jingwen.Study of occluded robust face recognition approach based on homotopy algorithm and color information fusion[J].Signal Processing,2011,27(11):1762-1767.
[8]Chen Jie,Zhang Yi.Sparse representation for face recognition by discriminative low-rank matrix recovery[J].Journal of Visual Communication and Image Representation,2014,25(5):763-773.
[9]江明阳,封举富.基于鲁棒主成分分析的人脸子空间重构方法[J].计算机辅助设计与图形学学报,2012,24(6):761-766.
Jiang Mingyang,Feng Jufu.Robust principal component analysis for face subspace recovery[J].Journal of Computer-Aided Design & Computer Graphics,2012,24(6):761-766.
[10]胡正平,彭燕,赵淑欢.非最小平方误差局部-全局加权融合的稀疏表示遮挡人脸识别[J].模式识别与人工智能学,2015,28(7):633-640.
Hu Zhengping,Peng Yan,Zhao Shuhuan.Sparse representation with weighted fusion of local based non-minimum square error and global for face recognition under occlusion condition[J].PR & AI,2015,28(7):633-640.
[11]Luan Xiao,Fang Bin,Liu Linghui,et al.Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion[J].Pattern Recognition,2014,47(2):495-508.
[12]邓楠,徐正光,王珺.基于稀疏表征多分类器融合的遮挡人脸识别[J].计算机应用研究,2013,30(6):1914-1916,1920.
Deng Nan,Xu Zhengguang,Wang Jun.Sparse representation based multi-classifier fusion approach for occluded face recognition[J].Application Research of Computers,2013,30(6):1914-1916,1920.
[13]杨国亮,丰义琴,鲁海荣.基于低秩表示中稀疏误差的可变光照和局部遮挡人脸识别[J].计算机工程与科学,2015,37(9):1742-1749.
Yang Guoliang,Feng Yiqin,Lu Hairong.Face recognition with varying illumination and occlusion based on sparse error of low rank representation[J].Computer Engineering & Science,2015,37(9):1742-1749.
[14]Hsieh Pingcheng,Tung Picheng.A novel hybrid approach based on sub-pattern technique and whitened PCA for face recognition[J].Pattern Recognition,2009,42(5):978-984.

相似文献/References:

[1]邓敏,韩玉启.基于数据推理和模式识别的财务困境预警模型[J].南京理工大学学报(自然科学版),2009,(06):833.
 DENG Min,HAN Yu-qi.Pre-warning Model of Financial Distress Based on Calculus Derivation and Pattern Recognition[J].Journal of Nanjing University of Science and Technology,2009,(04):833.
[2]邵黎,杨余旺.利用优化方法求解线性鉴别方程[J].南京理工大学学报(自然科学版),2005,(06):745.
 SHAO Li,YANG Yu-wang.Using Optimization Method to Solve Linear Discriminant Equations[J].Journal of Nanjing University of Science and Technology,2005,(04):745.
[3]束婷婷,甘岚,杨静宇.求解统计不相关的最佳鉴别矢量的统一算法[J].南京理工大学学报(自然科学版),2002,(03):290.
 ShuTingting GanLan YangJingyu.A Unified Algorithm for the Computation of Statistically Uncorrelated Optimal Discriminant Vectors[J].Journal of Nanjing University of Science and Technology,2002,(04):290.
[4]孙怀江,杨静宇.λ-模糊测度辨识方法研究[J].南京理工大学学报(自然科学版),2001,(01):44.
 SunHuaijiang YangJingyu.A Study on Identification Methods of λ-Fuzzy Measures[J].Journal of Nanjing University of Science and Technology,2001,(04):44.
[5]谭东宁,谭东汉.小样本机器学习理论:统计学习理论[J].南京理工大学学报(自然科学版),2001,(01):108.
 TanDongnin TanDonghan.Small-sample Machine Learning Theory: Statistical Learning Theory[J].Journal of Nanjing University of Science and Technology,2001,(04):108.
[6]聂伟荣,朱继南,赵玉霞.基于改进BP网络的地震动信号目标识别[J].南京理工大学学报(自然科学版),2000,(01):20.
 NieWeirong ZhuJinan ZhaoYuxia.Microseismic Signal Targets Identification Based on Improved BP Neural Networks[J].Journal of Nanjing University of Science and Technology,2000,(04):20.
[7]李宏东,李宏升,顾伟康.应用专门知识引导的联机自然手写汉字识别[J].南京理工大学学报(自然科学版),2000,(02):147.
 LiHongdong LiHongsheng GuWeikang.A Knowledge Based Algorithm for Online Cursive Chinese Character Recognition[J].Journal of Nanjing University of Science and Technology,2000,(04):147.
[8]李士进,杨静宇,金忠.基于离散隐马尔可夫模型和奇异值特征的人脸检测[J].南京理工大学学报(自然科学版),2000,(05):385.
 LiShijin YangJingyu JinZhong.Face Detection Based on Discrete Hidden Markov Models and Singular Value Feature[J].Journal of Nanjing University of Science and Technology,2000,(04):385.
[9]夏德深,金盛,王健.基于分数维与灰度梯度共生矩阵的气象云图识别(Ⅰ)——分数维对纹理复杂度和粗糙度的描述[J].南京理工大学学报(自然科学版),1999,(03):90.
 XiaDeshen JinSheng WangJian.Fractal Dimension and GGCM Based Meteorology Cloud Pictures Recognition Description of Texture Complexity and Roughness by Fractal Dimension (Ⅰ)[J].Journal of Nanjing University of Science and Technology,1999,(04):90.
[10]夏德深,金盛,王健.基于分数维与灰度梯度共生矩阵的气象云图识别(Ⅱ)——灰度梯度共生矩阵对纹理统计特征的描述[J].南京理工大学学报(自然科学版),1999,(04):289.
 XiaDeshen JinSheng WangJian.Fractal Dimension and GGCM Meteorology Cloud Pictures Recognition[J].Journal of Nanjing University of Science and Technology,1999,(04):289.

备注/Memo

备注/Memo:
收稿日期:2017-02-14 修回日期:2017-03-21基金项目:河南省教育科学“十二五”规划项目(2014JKGHC-0155)
作者简介:唐娴(1982-),女,硕士,讲师,主要研究方向:图像处理、网络安全、嵌入式系统,E-mail:tanxian20155@163.com; 通讯作者:黄军伟(1981-),男,讲师,主要研究方向:数据挖掘、深度学习、机器学习、神经网络等。
引文格式:唐娴,黄军伟.低秩鲁棒性主成分分析的遮挡人脸识别[J].南京理工大学学报,2017,41(4):460-465.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2017-08-31