Robust Regression Model Based on Low Rank Representation

doi:10.19678/j.issn.1000-3428.0053524

Computer Engineering ›› 2020, Vol. 46 ›› Issue (1): 74-79,86. doi: 10.19678/j.issn.1000-3428.0053524

Previous Articles Next Articles

Robust Regression Model Based on Low Rank Representation

WANG Lijuan^a, LI Keai^a, HAO Zhifeng^a, CAI Ruichu^a, YIN Ming^b

a. School of Computer;b. School of Automation, Guangdong University of Technology, Guangzhou 510006, China

Received:2018-12-28 Revised:2019-01-31 Online:2020-01-15 Published:2019-02-01

基于低秩表示的鲁棒回归模型

王丽娟^a, 李可爱^a, 郝志峰^a, 蔡瑞初^a, 尹明^b

广东工业大学 a. 计算机学院;b. 自动化学院, 广州 510006

作者简介:王丽娟(1978-),女,副教授,主研方向为数据挖掘、机器学习;李可爱,硕士;郝志峰、蔡瑞初、尹明,教授。
基金资助:
国家自然科学基金（61502108，61876042，61876043，61502175，61773130）；广东省自然科学基金（2014A030308008，2014A030306004）；NSFC-广东联合基金（U1501254）；广东省科技计划项目（2016B030306004，2017A010101024，2015B010131015）；广东省教育厅科研项目（2017KTSCX059）；广东省特支计划项目（2015TQ01X140）。

Abstract

Abstract: The existing linear regression method cannot effectively deal with noise and outliers.To address the problem,this paper establishes the LR RRM model by combining Low Rank Representation(LRR) and robust regression methods.The LRR method is used to detect noise and outliers in the data in a supervised way.The clean part of data is recovered from the low dimensional subspace of the original data and is used for the classification of linear regression,so as to improve the regression performance.Experimental results on the Extend YaleB,AR,ORL and PIE face datasets show that compared with the standard linear regression model,the robust principal component analysis based linear regression model and the LRR linear regression model,the proposed model has better classification accuracy and robustness on the four original dataset and the dataset with random noise.

Key words: linear regression, Low Rank Representation(LRR), noisy data, face recognition, high dimensional data

摘要： 现有的线性回归方法不能有效处理噪声和异常数据。针对这一问题，结合低秩表示和鲁棒回归方法构建模型LR-RRM。利用低秩表示方法以有监督的方式检测数据内的噪声和异常值，从原始数据的低维子空间中恢复数据干净部分，并将其应用于线性回归分类，从而提升回归性能。在Extend YaleB、AR、ORL和PIE人脸数据集上的实验结果表明，与标准线性回归、基于鲁棒主成分分析和低秩表示的线性回归模型相比，该模型在4种原始数据集以及添加随机噪声后的数据集上分类准确率和鲁棒性均较优。

关键词: 线性回归, 低秩表示, 噪声数据, 人脸识别, 高维数据

CLC Number:

TP391

WANG Lijuan, LI Keai, HAO Zhifeng, CAI Ruichu, YIN Ming. Robust Regression Model Based on Low Rank Representation[J]. Computer Engineering, 2020, 46(1): 74-79,86.

王丽娟, 李可爱, 郝志峰, 蔡瑞初, 尹明. 基于低秩表示的鲁棒回归模型[J]. 计算机工程, 2020, 46(1): 74-79,86.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0053524

http://www.ecice06.com/EN/Y2020/V46/I1/74

Figures/Tables 10

References

[1] WANG H,DING C,HUANG H.Multi-label linear discriminant analysis[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:126-139.
[2] HUANG S M,YANG J F.Improved principal component regression for face recognition under illumination variations[J].IEEE Signal Processing Letters,2012,19(4):179-182.
[3] PAPAGEORGIOU G,BOUBOULIS P,THEODORIDIS S.Robust linear regression analysis——a greedy approach[J].IEEE Transactions on Signal Processing,2015,63(15):3872-3887.
[4] HUANG Pu,LAI Zhihui,GAO Guangwei,et al.Adaptive linear discriminant regression classification for face recognition[J].Digital Signal Processing,2016,55:78-84.
[5] XIANG Shuo,ZHU Yunzhang,SHEN Xiaotong,et al.Optimal exact least squares rank minimization[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2012:480-488.
[6] CAI X,DING C,NIE F,et al.On the equivalent of low-rank linear regressions and linear discriminant analysis based regressions[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2013:1124-1132.
[7] HU Rongyao,LIU Xingyi,CHENG Debo,et al.Robust low-rank self-representation feature selection algorithm[J].Computer Engineering,2017,43(9):43-50.(in Chinese) 胡荣耀,刘星毅,程德波,等.鲁棒自表达的低秩属性选择算法[J].计算机工程,2017,43(9):43-50.
[8] VIDAL R,YI M,SASTRY S S.Generalized principal component analysis[M].Berlin,Germany:Springer,2016.
[9] LIU Guangcan,LIN Zhouchen,YAN Shuicheng,et al.Robust recovery of subspace structures by low-rank representation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(1):171-184.
[10] LIU Guangcan,LI Ping.Low-rank matrix completion in the presence of high coherence[J].IEEE Transactions on Signal Processing,2016,64(21):5623-5633.
[11] YANG Fangfang,WU Xisheng,GU Biaozhun.A face recognition algorithm based on low-rank subspace projection and Gabor feature via sparse representation[J].Computer Engineering and Science,2017,39(1):131-137.(in Chinese)杨方方,吴锡生,顾标准.基于低秩子空间投影和Gabor特征的稀疏表示人脸识别算法[J].计算机工程与科学,2017,39(1):131-137.
[12] XIE Hao.Research on subspace clustering algorithm based on low rank[D].Qingdao:Qingdao University,2018.(in Chinese)解昊.基于低秩性的子空间聚类算法研究[D].青岛:青岛大学,2018.
[13] WANG Rong.Face representation and classification based on reconstructed representation[D].Yangzhou:Yangzhou University,2017.(in Chinese)王蓉.基于重构表示的人脸图像表示与分类[D].扬州:扬州大学,2017.
[14] TAN Qunchao.Face recognition based on low rank matrix decomposition and sparde representation[J].Journal of Shandong University of Technology(Natural Science Edition),2017,31(4):36-40.(in Chinese)谭群超.基于低秩矩阵分解和稀疏表达的人脸识别方法[J].山东理工大学学报(自然科学版),2017,31(4):36-40.
[15] ZHU Yani,ZHU Chaoyang,LI Xiaoxin.Improved principal component analysis and linear regression classification for face recognition[J].Signal Processing,2017,145:175-182.
[16] YANG A Y,ZHOU Z,BALASUBRAMANIAN A G,et al.Fast L1-minimization algorithms for robust face recognition[J].IEEE Transactions on Image Processing,2013,22(8):3234-3246.
[17] WANG Yu,YIN Wotao,ZENG Jinshan.Global convergence of ADMM in nonconvex nonsmooth optimization[J].Journal of Scientific Computing,2019,78(1):29-63.
[18] CAI J F,CANDōS E J,SHEN Z.A singular value thresholding algorithm for matrix completion[J].SIAM Journal on optimization,2010,20(4):1956-1982.
[19] LEE K C,HO J,KRIEGMAN D J.Acquiring linear subspaces for face recognition under variable lighting[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2005,27(5):684-698.
[20] MARTÍNEZ A,BENAVENTE R.The AR face database[J].CVC Technical Report,1998,24:1-8.

Please choose a citation manager

Content to export