Low-rank tensor train for tensor robust principal component analysis. (English) Zbl 1433.90118
Summary: Recently, tensor train rank, defined by a well-balanced matricization scheme, has been shown the powerful capacity to capture the hidden correlations among different modes of a tensor, leading to great success in tensor completion problem. Most of the high-dimensional data in the real world are more likely to be grossly corrupted with sparse noise. In this paper, based on tensor train rank, we consider a new model for tensor robust principal component analysis which aims to recover a low-rank tensor corrupted by sparse noise. The alternating direction method of multipliers algorithm is developed to solve the proposed model. A tensor augmentation tool called ket augmentation is used to convert lower-order tensors to higher-order tensors to enhance the performance of our method. Experiments of simulated data show the superiority of the proposed method in terms of PSNR and SSIM values. Moreover, experiments of the real rain streaks removal and the real stripe noise removal also illustrate the effectiveness of the proposed method.
MSC:
| 90C25 | Convex programming |
| 65K10 | Numerical optimization and variational techniques |
| 62H25 | Factor analysis and principal components; correspondence analysis |
| 94A08 | Image processing (compression, reconstruction, etc.) in information and communication theory |
Keywords:
tensor robust principal component analysis; tensor train rank; high-dimensional data; alternating direction method of multipliersReferences:
| [1] | Zhang, X. J., A nonconvex relaxation approach to low-rank tensor completion, IEEE Trans. Neural Netws. Learn. Syst. (2018) |
| [2] | Zhao, Q. B.; Zhang, L. Q.; Cichocki, A., Bayesian CP factorization of incomplete tensors with automatic rank determination, IEEE Trans. Pattern Anal., 37, 9, 1751-1763 (2015) |
| [3] | Fu, X.; Huang, K. J.; Yang, B.; Ma, W. K.; Sidiropoulos, N. D., Robust volume minimization-based matrix factorization for remote sensing and document clustering, IEEE Trans. Signal Process., 64, 23, 6254-6268 (2016) · Zbl 1414.94205 |
| [4] | Yang, J. H.; Zhao, X. L.; Mei, J. J.; Wang, S.; Ma, T. H.; Huang, T. Z., Total variation and high-order total variation adaptive model for restoring blurred images with cauchy noise, Comput. Math. Appl., 77, 5, 1255-1272 (2019) · Zbl 1442.94015 |
| [5] | Lu, H. Y.; Li, S. Q.; Liu, Q. G.; Zhang, M. H., Mf-lrtc: multi-filters guided low-rank tensor coding for image restoration research article, Neurocomputing, 303, 88-102 (2018) |
| [6] | Oliveira, R. V.; Pereira, J. S., The role of diffusion magnetic resonance imaging in Parkinson’s disease and in the differential diagnosis with atypical parkinsonism, Radiol. Bras., 50, 4, 250-257 (2017) |
| [7] | Chang, Y.; Yan, L. X.; Wu, T.; Zhong, S., Remote sensing image stripe noise removal: from image decomposition perspective, IEEE Trans. Geosci. Remote Sens., 54, 12, 7018-7031 (2016) |
| [8] | Chen, Y.; Huang, T. Z.; Zhao, X. L., Destriping of multispectral remote sensing image using low-rank tensor decomposition, IEEE J. STARS, 11, 12, 4950-4967 (2018) |
| [9] | Ji, T. Y.; Huang, T. Z.; Zhao, X. L.; Ma, T. H.; Liu, G., Tensor completion using total variation and low-rank matrix factorization, Inf. Sci., 326, 243-257 (2016) · Zbl 1387.94038 |
| [10] | Jiang, T. X.; Huang, T. Z.; Zhao, X. L.; Deng, L. J.; Wang, Y., A novel video rain streak removal method using directional gradient priors, IEEE Trans. Image Process., 28, 4, 2089-2102 (2019) |
| [11] | Wang, Y. T.; Zhao, X. L.; Jiang, T. X.; Deng, L. J.; Zhang, Y. T., A total variation and group sparsity based tensor optimization model for video rain streak removal, Signal Process. Image Commun., 73, 96-108 (2019) |
| [12] | Zheng, Y. B.; Huang, T. Z.; Ji, T. Y.; Zhao, X. L.; Jiang, T. X.; Ma, T. H., Low-rank tensor completion via smooth matrix factorization, Appl. Math. Model., 70, 677-695 (2019) · Zbl 1462.90096 |
| [13] | Jia, Z.; Ng, M.; Song, G., Robust quaternion matrix completion with applications to image inpainting, Numer. Linear Algebra (2019) · Zbl 1474.65126 |
| [14] | Eckart, C.; Young, G., The approximation of one matrix by another of lower rank, Psychometrika, 1, 3, 211-218 (1936) · JFM 62.1075.02 |
| [15] | Candés, E. J.; Li, X. D.; Ma, Y.; Wright, J., Robust principal component analysis?, J. ACM, 58, 3, 1-37 (2011) · Zbl 1327.62369 |
| [16] | Cao, W. F.; Wang, Y.; Sun, J.; Meng, D. Y.; Yang, C.; Cichocki, A.; Xu, Z. B., Total variation regularized tensor RPCA for background subtraction from compressive measurements, IEEE Trans. Image Process., 25, 9, 4075-4090 (2016) · Zbl 1408.94065 |
| [17] | Huang, B.; Mu, C.; Goldfarb, D.; Wright, J., Provable models for robust low-rank tensor completion, Pac. J. Optim., 11, 2, 339-364 (2015) · Zbl 1323.15019 |
| [18] | Lu, C. Y.; Feng, J. S.; Chen, Y. D.; Liu, W.; Lin, Z. C.; Yan, S. C., Tensor robust principal component analysis: exact recovery of corrupted low-rank tensors via convex optimization, Proceedings of the CVPR, 5249-5257 (2016) |
| [19] | Zhao, Q.; Meng, D. Y.; Xu, Z. B.; Gao, C. Q., A block coordinate descent approach for sparse principal component analysis, Neurocomputing, 153, 180-190 (2015) |
| [20] | Kolda, T. G.; Bader, B. W., Tensor decompositions and applications, SIAM Rev., 51, 3, 455-500 (2009) · Zbl 1173.65029 |
| [21] | Tan, H. C.; Cheng, B.; Wang, W. H.; Zhang, Y. J.; Ran, B., Tensor completion via a multi-linear low-n-rank factorization model, Neurocomputing, 133, 161-169 (2014) |
| [22] | Liu, J.; Musialski, P.; Wonka, P.; Ye, J., Tensor completion for estimating missing values in visual data., IEEE Trans. Pattern Anal., 35, 1, 208-220 (2013) |
| [23] | Bengua, J. A.; Phien, H. N.; Tuan, H. D.; Do, M. N., Efficient tensor completion for color image and video recovery: low-rank tensor train, IEEE Trans. Image Process., 26, 5, 2466-2479 (2017) · Zbl 1409.94036 |
| [24] | Zhang, Z. M.; Ely, G.; Aeron, S.; Hao, N.; Kilmer, M., Novel methods for multilinear data completion and de-noising based on tensor-SVD, Proceedings of the CVPR, 44, 3842-3849 (2014) |
| [25] | Kilmer, M. E.; Braman, K.; Hao, N.; Hoover, R. C., Third-order tensors as operators on matrices: a theoretical and computational framework with applications in imaging, SIAM J. Matrix Anal. A, 34, 1, 148-172 (2013) · Zbl 1269.65044 |
| [26] | Semerci, O.; Hao, N.; Kilmer, M. E.; Miller, E. L., Tensor-based formulation and nuclear norm regularization for multienergy computed tomography, IEEE Trans. Image Process., 23, 4, 1678-1693 (2014) · Zbl 1374.94335 |
| [27] | Zhang, Z. M.; Aeron, S., Exact tensor completion using T-SVD, IEEE Trans. Signal Process., 65, 6, 1511-1526 (2017) · Zbl 1414.94741 |
| [28] | Lee, N.; Cichocki, A., Estimating a few extreme singular values and vectors for large-scale matrices in tensor train format, SIAM J. Matrix Anal. A, 36, 3, 994-1014 (2015) · Zbl 1319.65029 |
| [29] | Rauhut, H.; Schneider, R.; Željka, S., Tensor completion in hierarchical tensor representations, Compressed Sensing and Its Applications, 419-450 (2015), Springer · Zbl 1333.94023 |
| [30] | Oseledets, I. V., Tensor-train decomposition, SIAM J. Sci. Comput., 33, 5, 2295-2317 (2011) · Zbl 1232.15018 |
| [31] | Bengua, J. A.; Tuan, H. D.; Phien, H. N.; Do, M. N., Concatenated image completion via tensor augmentation and completion, Proceedings of the ICSPCS, 1-7 (2016) |
| [32] | Fazel, M.; Kei, P. T.; Sun, D.; Tseng, P., Hankel matrix rank minimization with applications to system identification and realization, SIAM J. Matrix Anal. A, 34, 3, 946-977 (2013) · Zbl 1302.90127 |
| [33] | Ding, M.; Huang, T. Z.; Wang, S.; Mei, J. J.; Zhao, X. L., Total variation with overlapping group sparsity for deblurring images under cauchy noise, Appl. Math. Comput., 341, 128-147 (2019) · Zbl 1428.94021 |
| [34] | Goncalves, M. L.N., On the pointwise iteration-complexity of a dynamic regularized ADMM with over-relaxation stepsize, Appl. Math. Comput., 336, 315-325 (2018) · Zbl 1427.90216 |
| [35] | Zhao, X. L.; Wang, W.; Zeng, T. Y.; Huang, T. Z.; Ng, M. K., Total variation structured total least squares method for image restoration, SIAM J. Sci. Comput., 35, 6, 1304-1320 (2013) · Zbl 1287.65014 |
| [36] | Bertsekas, D. P.; Nedic, A.; Ozdaglar, A. E., Convex Analysis and Optimization (2013), Athena Scientific |
| [37] | Ma, T. H.; Huang, T. Z.; Zhao, X. L., Group-based image decomposition using 3-D cartoon and texture priors, Inf. Sci., 328, 510-527 (2016) |
| [38] | Zhao, X. L.; Wang, F.; Ng, M. K., A new convex optimization model for multiplicative noise and blur removal, SIAM J. Imaging Sci., 7, 1, 456-475 (2014) · Zbl 1296.65093 |
| [39] | Li, C.; Wang, C. L.; Wang, J., Convergence analysis of the augmented Lagrange multiplier algorithm for a class of matrix compressive recovery, Appl. Math. Lett., 59, 12-17 (2016) · Zbl 1381.94035 |
| [40] | Ma, S.; Goldfarb, D.; Chen, L., Fixed point and Bregman iterative methods for matrix rank minimization, Math. Programm., 128, 1-2, 321-353 (2009) · Zbl 1221.65146 |
| [41] | Huang, B.; Mu, C.; Goldfarb, D.; Wright, J., Provable models for robust low-rank tensor completion, Pac. J. Optim., 11, 2, 339-364 (2015) · Zbl 1323.15019 |
| [42] | Chen, D. L.; Chen, Y. Q.; Xue, D. Y., Fractional-order total variation image denoising based on proximity algorithm, Appl. Math. Comput., 257, 537-545 (2015) · Zbl 1338.68273 |
| [43] | Liu, R. W.; Shi, L.; Huang, W.; Xu, J.; Yu, S. C.; Wang, D., Generalized total variation-based MRI Rician denoising model with spatially adaptive regularization parameters, Magn. Reson. Imaging, 32, 6, 702-720 (2014) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
