Advertisement

Circuits, Systems, and Signal Processing

, Volume 37, Issue 9, pp 3827–3841 | Cite as

An Iterative Method for Tensor Inpainting Based on Higher-Order Singular Value Decomposition

  • S. F. Yeganli
  • R. Yu
  • H. Demirel
Article
  • 189 Downloads

Abstract

We consider the problem of tensor (i.e., multidimensional array) inpainting in this paper. By using higher-order singular value decomposition, we propose an iterative algorithm that performs soft thresholding on entries of the core tensor and then reconstructs via the directional orthogonal matrices. An inpainted tensor is obtained at the end of the iteration. Simulations conducted over color images, video frames, and MR images validate that the proposed algorithm is competitive with state-of-the-art completion algorithms. The evaluation is made in terms of quality metrics and visual comparison.

Keywords

Higher-order singular value decomposition Inpainting Soft thresholding Tensor completion 

References

  1. 1.
    M.V. Alfonso, J.M. Bioucas-Dias, M.A.T. Figueiredo, Fast image recovery using variable splitting and constrained optimization. IEEE Trans. Image Process. 19(9), 2345–2356 (2010)MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    J. Ballani, L. Grasedyck, M. Kluge, Black box approximation of tensors in hierarchical Tucker format. Linear ALgebra Appl. 438(2), 639657 (2013)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    M. Bertalmio, A. Bertozzi, G. Sapiro, Navier-stokes, fluid dynamics, and image and video inpainting. Proc. IEEE Comp. Vis. Pattern Recogn. 1, 355–362 (2001)Google Scholar
  4. 4.
    M. Bertalmio, G. Sapiro, V. Caselles, C. Ballester, Image inpainting. Comput. Graph. SIGGRAPH 2000, 417–424 (2000)Google Scholar
  5. 5.
    J.F. Cai, E.J. Candes, Z. Shen, A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    J.F. Cai, H. Ji, F. Shang, Z. Shen, Inpainting for compressed images. Appl. Comput. Harmon. Anal. 29(3), 368–381 (2010)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    C.F. Caiafa, A. Cichocki, Multidimensional compressed sensing and their applications. Data Min. Knowl. Discov. 3(6), 355–380 (2013)CrossRefGoogle Scholar
  8. 8.
    C.F. Caiafa, A. Cichocki, Computing sparse representations of multidimensional signals using kronecker bases. Neural Comput. J. 25(1), 186–220 (2013)MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    E.J. Candes, B. Recht, Exact matrix completion via convex optimization. Commun. ACM 55(6), 111–119 (2012)CrossRefMATHGoogle Scholar
  10. 10.
    Y.L. Chen, C.T. Hsu, H.Y.M. Liao, Simultaneous tensor decomposition and completion using factor priors. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 577–591 (2014)CrossRefGoogle Scholar
  11. 11.
    A. Cichocki, D. Mandic, L.D. Lathauwer, G. Zhou, Q. Zhao, C. Caiafa, H.A. Phan, Tensor decompositions for signal processing applications from two-way to multiway component analysis. IEEE Signal Process. Mag. 32(2), 145–163 (2015)CrossRefGoogle Scholar
  12. 12.
    A. Criminisi, P. Perez, K. Toyama, Region filling and object removal by exemplar-based inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)CrossRefGoogle Scholar
  13. 13.
    M. Elad, J.L. Starck, P. Querre, D.L. Donoho, Simultaneous cartoon and texture image inpainting using morphological analysis (MCA). Appl. Comput. Harmon. Anal. 19(3), 340–358 (2005)MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    N. Eslahi, A. Aghagolzadeh, Compressive sensing image restoration using adaptive curvelet thresholding and nonlocal sparse regularization. IEEE Trans. Image Process. 25(7), 3126–3140 (2016)MathSciNetCrossRefGoogle Scholar
  15. 15.
    M.J. Fadili, J.L. Starck, F. Murtagh, Inpainting and zooming using sparse representation. Comput. J. 52(1), 64–79 (2007)CrossRefGoogle Scholar
  16. 16.
    M.S. Farid, H .Khan , A. Mahmood, Image inpainting based on pyramids, in IEEE 10th International Conference on Signal Processing (2010)Google Scholar
  17. 17.
    G. Favier, A.L.F. de Almeida, Overview of constrained PARAFAC models. EURASIP J. Adv. Signal Process 1(142) (2014).  https://doi.org/10.1186/1687-6180
  18. 18.
    M. Filipovic, A. Jukic, Tucker factorization with missing data with application to low-n-rank tensor completion. Multidimens. Syst. Signal Process. 26(3), 677–692 (2015)CrossRefGoogle Scholar
  19. 19.
    S. Gandy, B. Recht, I. Yamada, Tensor completion and low-n-rank tensor recovery via convex optimization. Inverse Probl. 27(2), 025010 (2011)MathSciNetCrossRefMATHGoogle Scholar
  20. 20.
    M. Ghorai, B. Chanda, An image inpainting algorithm using higher order singular value decomposition, in 22nd International Conference on Pattern Recognition, pp. 2867–2872 (2014)Google Scholar
  21. 21.
    M. Ghorai, S. Mandal, B. Chanda (2014) A two-step image inpainting algorithm using tensor SVD. Computer Vision-ACCV 2014 Workshops, Vol. 2, pp. 63–77 (2014)Google Scholar
  22. 22.
    W. Gong, H. Li, D. Zhao, An Improved denoising model based on the analysis K-SVD algorithm. Circuits Syst. Signal Process. 36(10), 4006–4021 (2017)CrossRefGoogle Scholar
  23. 23.
    F. Gu, H. Zhang, W. Wang, D. Zhu, PARAFAC-Based blind identification of underdetermined mixtures using gaussian mixture model. Circuits Syst. Signal Process. 33(6), 1841–1857 (2014)MathSciNetCrossRefGoogle Scholar
  24. 24.
    C. Guillemot, O.L. Meur, Image inpainting: overview and recent advances. IEEE Signal Process. Mag. 31(1), 127–144 (2014)CrossRefGoogle Scholar
  25. 25.
    C. Guillemot, M. Turkan, O.L. Meur, M. Ebdelli, Object removal and loss concealment using neighbor embedding methods. Signal Process. Image Commun. 28(10), 1405–1419 (2013)CrossRefGoogle Scholar
  26. 26.
    L.T. Huang, A.L.F. de Almeida, H.C. So, Target estimation in bistatic MIMO radar via tensor completion. Signal Process. 120, 654–659 (2016)CrossRefGoogle Scholar
  27. 27.
    B. Jiang, F. Yang, S. Zhang, Tensor and its Tucker core: the invariance relationships. Numer. Linear Algebra Appl. 24(3), 1253–1278 (2017)MathSciNetCrossRefMATHGoogle Scholar
  28. 28.
    A. Karfoul, L. Albera, L.D. Lathauwer, Iterative methods for the canonical decomposition of multi-way arrays: application to blind underdetermined mixture identification. Signal Process. 91(8), 1789–1802 (2011)CrossRefMATHGoogle Scholar
  29. 29.
    V. Katkovnik , M. Ponomarenko, K. Egiazarian, Complex domain nonlocal block-matching denoising based on high-order singular value decomposition (HOSVD), in 25th European Signal Processing Conference (2017)Google Scholar
  30. 30.
    T.G. Kolda, B.W. Bader, Tensor decomposition and application. SIAM Rev. 51(3), 455–500 (2009)MathSciNetCrossRefMATHGoogle Scholar
  31. 31.
    K. Konishi, K. Uruma, T. Takahashi, T. Furukawa, Iterative partial matrix shrinkage algorithm for matrix rank minimization. Signal Process. 100, 124–131 (2014)CrossRefGoogle Scholar
  32. 32.
    L.D. Lathauwer, B. De Moor, J. Vandewalle, Multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253–1278 (2000)MathSciNetCrossRefMATHGoogle Scholar
  33. 33.
    A. Li, D. Chen, K. Lin, G. Sun, Nonlocal joint regularizations framework with application to image denoising. Circuits Syst. Signal Process. 35(8), 2932–2942 (2016)CrossRefGoogle Scholar
  34. 34.
    A. Li, D. Chen, G. Sun, K. Lin, Sparse representation-based image restoration via nonlocal supervised coding. Opt. Rev. 23(5), 776–783 (2016)CrossRefGoogle Scholar
  35. 35.
    Y. Li, J. Yan, Y. Zhou, J. Yan, Optimum subspace learning and error correction for tensors. Comput Vis. ECCV 2010, 790–803 (2010)Google Scholar
  36. 36.
    J. Liu, P. Musialski, P. Wonka, J .Ye, Tensor completion for estimating missing values in visual data, in Proceedings of 12th IEEE International Conference on Computer Vision, pp. 2114–2121 (2009)Google Scholar
  37. 37.
    J. Liu, P. Musialski, P. Wonka, J. Ye, Tensor completion for estimating missing values in visual data. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 208–220 (2013)CrossRefGoogle Scholar
  38. 38.
    Y. Liu, F. Shang, W .Fan, J. Cheng, H. Cheng, Generalized higher-order orthogonal iteration for tensor decomposition and completion, in Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) 27, pp. 1763–1771 (2014)Google Scholar
  39. 39.
    S. Ma, D. Goldfard, L. Chen, Fixed point and Bregman iterative methods for matrix rank minimization. J. Math. Program. 128(1), 321–353 (2011)MathSciNetCrossRefMATHGoogle Scholar
  40. 40.
    A. Rajwade, A. Rangarajan, A. Banerjee, Using the higher order singular value decomposition for video denoising, in EMMCVPR’11 Proceedings of the 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 344–354 (2011)Google Scholar
  41. 41.
    A. Rajwade, A. Rangarajan, A. Banerjee, Image denoising using the higher order singular value decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 35(4), 849–862 (2013)CrossRefGoogle Scholar
  42. 42.
    H. Rauhut, R. Schneider, Z. Stojanac, Low-rank tensor recovery via iterative hard thresholding, in Proceedings of the International Conference on Sampling Theory and Applications (2013)Google Scholar
  43. 43.
    M. Signoretto, R. Van De Plas, B. De Moor, J.A.K. Suykens, Tensor versus matrix completion: a comparison with application to spectral data. IEEE Signal Process. Lett. 18(7), 403–406 (2011)CrossRefGoogle Scholar
  44. 44.
    G. Suryanarayana, R. Dhuli, Super-resolution image reconstruction using dual-mode complex diffusion-based shock filter and singular value decomposition. Circuits Syst. Signal Process. 36(8), 3409–3425 (2017)CrossRefGoogle Scholar
  45. 45.
    H. Tan, B. Cheng, W. Wang, Y.J. Zhang, B. Ran, Tensor completion via a multi-linear low-n-rank factorization model. Neurocomputing 133, 161–169 (2014)CrossRefGoogle Scholar
  46. 46.
    A. Telea, An image inpainting technique based on the fast marching method. J. Graph. Tools 9(1), 23–34 (2004)CrossRefGoogle Scholar
  47. 47.
    Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  48. 48.
    Y. Wei, S. Liu, Domain-based structure-aware image inpainting. Signal Image Video Process. 10(5), 911–919 (2016)MathSciNetCrossRefGoogle Scholar
  49. 49.
    S.F. Yeganli, H. Demirel, R. Yu, Noise removal from MR images via iterative regularization based on higher-order singular value decomposition. Signal Image Video Process. 11(8), 1477–1484 (2017)CrossRefGoogle Scholar
  50. 50.
    S.F. Yeganli , R. Yu, Image inpainting via singular value thresholding, in 21st Signal Processing and Communication Application Conference (SIU), Kyrenia, Cyprus, pp. 1–4 (2013)Google Scholar
  51. 51.
    Q. Zhao, L. Zhang, A. Cichocki, Bayesian CP factorization of incomplete tensors with automatic rank determination. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1751–1763 (2015)CrossRefGoogle Scholar
  52. 52.
    J. Zhou, S. Liu, G. Qiu, F. Zhang, J. Sun, Tensor missing value recovery with tucker thresholding method, in 5th International Conference on Intelligent Networks and Collaborative Systems, pp. 716–720 (2013)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Electrical and Electronic Engineering DepartmentEastern Mediterranean UniversityGazimagusa, via Mersin 10Turkey

Personalised recommendations