Abstract
Robust principal component analysis (RPCA) based methods via decomposition into low-rank plus sparse matrices offer a wide range of applications for image processing, video processing and 3D computer vision. Most of the time the observed imagery data is often arbitrarily corrupted by anything such as large sparse noise, small dense noise and other unknown fraction, which we call mixed noise in this paper. However, low rank matrix recovery by RPCA is born for the existence of large sparse noise, so its performance and applicability are limited in the presence of mixed noise. In this paper, a generalized robust principal component analysis with norm \(l_{2,1}\) model is proposed to solve the problem of low-rank matrix recovery under mixed large sparse noise and small dense noise. The corrupted matrix is written as a combination that minimizes the nuclear norm, the 1-norm and the norm \(l_{2,1}\), which has high efficiency, flexibility and robustness for low rank matrix recovery from mixed noise. Then a novel and efficient algorithm called random permutation alternative direction of multiplier method is applied to solve the model. Experiments with simulations and real datasets demonstrate efficiency and robustness of this model and algorithm.
Similar content being viewed by others
References
Alpaydin E (2004) Introduction to Machine Learning (Adaptive Computation and Machine Learning) [M]. Introduction to machine learning. MIT, Oxford, p 28
Chong P, Kang Z, Yang M et al (2016) RAP: scalable RPCA for low-rank matrix recovery[C]. In: Proceedings of the 2016 ACM conference on information and knowledge management, pp. 2113–2118
Cands EJ, Li X, Ma Y et al (2011) Robust principal component analysis? [J]. JACM 58(3):1–37
Cands EJ, Recht B (2009) Exact matrix completion via convex optimization[J]. Found Comput Math 9(6):717–772
Wright J, Ganesh A, Rao S et al (2009) Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization[C]. In: Advances in neural information processing systems, pp 2080–2088
Lin Z, Chen M, Ma Y (2010) The Augmented Lagrange Multiplier method for exact recovery of corrupted low-rank matrices [J]. Eprint Arxiv, p 9
Recht B, Fazel M, Parrilo P (2010) Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization [J]. SIAM Rev 52(3):471–501
Hu Y, Zhang D, Li X et al (2013) Fast and Accurate Matrix Completion via Truncated Nuclear Norm Regularization [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence 35(9):2117–2130
Lin Z, Xu C, Zha H (2018) Robust matrix factorization by majorization minimization [J]. IEEE Trans Pattern Anal Mach Intell 40(1):208–220
Qian W, Cao F (2019) Adaptive algorithms for low-rank and sparse matrix recovery with truncated nuclear norm [J]. Int J Mach Learn Cybern 10(6):1341–1355
Xue Z, Dong J, Zhao Y et al (2019) Low-rank and sparse matrix decomposition via the truncated nuclear norm and a sparse regularizer [J]. Vis Comput 35(11):1549–1566
Li J, Zhao LN, Hou XK (2017) Matrix recovery by randomly permuted alternating direction method of multipliers[J]. J Beijing Univ Chem Technol 44(3):123–128
Zhao JX, Zhao LN (2019) Low-rank and sparse matrices fitting algorithm for low-rank representation. Comput Math Appl. https://doi.org/10.1016/j.camwa.2019.07.012
Lin Z, Ganesh A, Wright J et al (2009) Fast convex optimization algorithms for exact recovery of a corrupted low-rank matrix [J]. CAMSAP 56(3):707–722
Glowinski R (2014) On alternating direction methods of multipliers: a historical perspective [M]. Modeling, simulation and optimization for science and technology. Springer, Netherlands, pp 59–82
Zhao JX, Feng Q, Zhao LN (2019) Alternating direction and Taylor expansion minimization algorithms for unconstrained nuclear norm optimization[J]. Num Algorithms 82:371–396
Li J, Zhao L, Zhang M et al (2017) Low rank matrix recovery from sparse noise by 2,1 loss function[C]. In: IEEE International conference on signal & image processing
Li Z, Liu J, Tang J et al (2015) Robust structured subspace learning for data representation[J]. IEEE Trans Pattern Anal Mach Intell 37(10):2085–2098
Sun R, Luo ZQ, Ye Y (2015) On the expected convergence of randomly permuted ADMM [J]. Mathematics. arXiv:1503.06387
Li Y, Liu G, Liu Q et al (2018) Moving object detection via segmentation and saliency constrained RPCA [J]. Neurocomputing 323:352–362
Han G, Wang J, Cai X (2017) Background subtraction based on modified online robust principal component analysis [J]. Int J Mach Learn Cybern 8(6):1839–1852
Bouwmans T et al (2018) On the applications of robust PCA in image and video processing. Proc IEEE 106(8):1427–1457
Gu S, Xie Q, Meng D et al (2017) Weighted nuclear norm minimization and its applications to low level vision [J]. Int J Comput Vis 121(2):183–208
Cands EJ, Tao T (2010) The power of convex relaxation: near-optimal matrix completion [J]. IEEE Trans Inf Theory 56(5):2053–2080
Deng Y et al (2018) Nuclear norm-based matrix regression preserving embedding for face recognition [J]. Neurocomputing 311:279–290
Tan X, Chen S, Zhou ZH et al (2006) Face recognition from a single image per person: a survey [J]. Pattern Recog 39(9):1725–1745
Dolhansky Brian, Ferrer Cristian Canton (2018) Eye in-painting with exemplar Generative Adversarial Networks [C]. CVPR
Etemad K, Chellappa R (1997) Discriminant analysis for recognition of human face images [J]. J. Opt. Soc. Am. A 14(8):1724–1733
Guo G, Li SZ, Chan K (March 2000) Face recognition by support vector machines[C]. Proc. of the IEEE Int. Conf. on Automatic Face and Gesture Recognition, 196-201
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding [J]. Science 290(5500):2323–2326
Wright J, Yang AY, Ganesh A et al (2009) Robust face recognition via sparse representation [J]. IEEE Trans. Pattern Anal. Mach. Intell. 31(2):210–227
Acknowledgements
The work is supported by the National Natural Science Foundation of China 11301021 and 11571031.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhao, L., Hou, X., Yang, H. et al. GRPCA21 for recovering a corrupted low-rank matrix. Int. J. Mach. Learn. & Cyber. 11, 1293–1305 (2020). https://doi.org/10.1007/s13042-019-01039-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-019-01039-9