Skip to main content
SpringerLink
Log in

Improving image inpainting quality by a new SVD-based decomposition

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this paper, we present a new algorithm for image inpainting using structure and texture information. Our image decomposition to texture and structure is accomplished by the SVD method in the primary step, and then an algorithm for texture inpainting is applied. At the next level, edge detection is used in target region related to inpainted texture component. The detected edges demonstrate border of different textures in the target region, and the boundary pixels are ignored from mask temporarily. The other target pixels should be primarily inpainted, and then border pixels would be filled subsequently. Experimental results of this algorithm show better consistency in comparison with state of the art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Alilou VK, Yaghmaee F (2017) Exemplar-based image inpainting using svd-based approximation matrix and multi-scale analysis. Multimed Tools Appl 76(5):7213–7234

    Article  Google Scholar 

  2. Alotaibi N, Labrosse F (2015) Image completion by structure reconstruction and texture synthesis. Pattern Anal Applic 18(2):333–350

    Article  MathSciNet  Google Scholar 

  3. Ballester C, Bertalmio M, Caselles V, Sapiro G, Verdera J (2001) Filling-in by joint interpolation of vector fields and gray levels. IEEE Trans Image Process 10(8):1200–1211

    Article  MathSciNet  Google Scholar 

  4. Bengua JA, Phien HN, Tuan HD, Do MN (2017) Efficient tensor completion for color image and video recovery: low-rank tensor train. IEEE Trans Image Process 26:2466–2479

    Article  MathSciNet  Google Scholar 

  5. Bertalmio M, Sapiro G, Caselles V, and Ballester C (2000) Image Inpainting. SIGGRAPH’00: Proceedings of the 27th annual conference on Computer graphics and interactive techniques, pp 417–424. https://doi.org/10.1145/344779.344972

  6. Bertalmio M, Vese L, Sapiro G, Osher S (2003) Simultaneous structure and texture image Inpainting. IEEE Trans Image Process 12:882–889

    Article  Google Scholar 

  7. Bornemann F, März T (2007) Fast image Inpainting based on coherence transport. J Math Imaging Vis 28(3):259–278

    Article  MathSciNet  Google Scholar 

  8. Buyssens P, Daisy M, Tschumperlé D, Lézoray O (2015) Exemplar-based Inpainting: technical review and new heuristics for better geometric reconstructions. IEEE Trans Image Process 24(6):1809–1824

  9. Chan TF, Shen J (2001) Nontexture Inpainting by curvature-driven diffusions. J Vis Commun Image Represent 12(4):436–449

    Article  Google Scholar 

  10. Chen Z et al (2016) Structure aware image inpainting using patch scale optimization. J Vis Commun Image Represent 40:312–323

    Article  Google Scholar 

  11. Criminisi A, Pérez P, Toyama K (2004) Region filling and object removal by exemplar-based image inpainting. IEEE Trans Image Process 13:1200–1212

    Article  Google Scholar 

  12. Darabi S, Shechtman E, Barnes C, Goldman DB (2012) Image melding: combining inconsistent images using patch-based synthesis. ACM Trans Graph 31(4):82:1–82:10

    Article  Google Scholar 

  13. Efros AA, Leung TK (1999) Texture synthesis by nonparametric sampling, in IEEE Int. Conf. Computer Vision

  14. Fan Q, Zhang L (2018) A novel patch matching algorithm for exemplar-based image inpainting. Multimed Tools Appl 77(9):10807–10821

    Article  Google Scholar 

  15. Fazel M, “Matrix rank minimization with applications,” PhD thesis, Stanford University, 2002

  16. Ghorai M, Mandal S, Chanda B 2014 A two-step image inpainting algorithm using tensor svd. In: Computer Vision-ACCV 2014 Workshops, pp 63–77

    Chapter  Google Scholar 

  17. Golub GH, VanLoan CF (1996) Matrix computations. The Johns Hopkins Univ. Press, Baltimore

  18. Guo Q, Gao S, Zhang X, Yin Y, Zhang C (2017) Patch-based image Inpainting via two-stage low rank approximation. IEEE Trans Vis Comput Graph 24(2018):2023–2036

    Article  Google Scholar 

  19. He K and Sun J (2012) Statistics of patch offsets for image completion, European Conference on Computer Vision (ECCV), pp.16–29

    Chapter  Google Scholar 

  20. He K, Sun J (2014) Image completion approaches using the statistics of similar patches. IEEE Trans Pattern Anal Mach Intell 36(12):2423–2435

    Article  Google Scholar 

  21. He L, Wang Y (2014) Iterative support detection-based split Bregman method for wavelet frame-based image inpainting. IEEE Trans Image Process 23(12):5470–5485

    Article  MathSciNet  Google Scholar 

  22. Isogawa M, Mikami D, Takahashi K, Kojima A (2017) Image and Video completion via feature reduction and compensation. Multimed Tools Appl 76:9443–9462

    Article  Google Scholar 

  23. Jin X et al (2018) Sparsity-Based Image Inpainting detection via canonical correlation analysis with low-rank constraints. IEEE Access 6:49967–49978

    Article  Google Scholar 

  24. Kumar V, Mukherjee J, Das Mandal SK (2016) Image Inpainting through metric Labelling via guided patch mixing. IEEE Trans Image Process 25(11):5212–5226

    Article  MathSciNet  Google Scholar 

  25. Lee J, Lee DK, Park RH (2012) Robust exemplar-based inpainting algorithm using region segmentation. IEEE Trans Consum Electron 58(2):553–561

    Article  Google Scholar 

  26. Levin A, Zomet A, Weiss Y (2003) Learning how to inpaint from global image statistics, International Conference on Computer Vision (ICCV), pp. 305–312

  27. Liang X, Ren X, Zhang Z, Ma Y (2016) Texture repairing by unified low rank optimization. J Comput Sci Technol 31(3):525–546

    Article  MathSciNet  Google Scholar 

  28. Liu J, Musialski P, Wonka P, Ye J (2013) Tensor completion for estimating missing values in visual data. IEEE Trans Pattern Anal Mach Intell 35(1):208–220

    Article  Google Scholar 

  29. Moonen M, Dooren PV, Vandewalle J (1992) A singular value decomposition updating algorithm for subspace tracking. SIAM J Matrix Anal Appl 13(4):1015–1038

    Article  MathSciNet  Google Scholar 

  30. Ogawa T, Haseyama M (2013) Image inpainting based on sparse representations with a perceptual metric. EURASIP J Adv Signal Process 179(2013). https://doi.org/10.1186/1687-6180-2013-179

  31. Padmavathi S, Priyalakshmi B, Soman KP (2012) Hirarchical digital image Inpainting using wavelets. SIPIJ 3(4):85–93

    Google Scholar 

  32. Qin C, Wang S, Zhang X (2012) Simultaneous inpainting for image structure and texture using anisotropic heat transfer model. Multimed Tools Appl 56(3):469–483

    Article  Google Scholar 

  33. Ruzic T, Pizurica A (2015) Context-aware patch based image inpainting using Markov random field modeling. IEEE Trans Image Process 24(1):444–456

    Article  MathSciNet  Google Scholar 

  34. Shen J, Chan TF (2002) Mathematical models for local nontexture Inpaintings. SIAM 62:1019–1043

    MathSciNet  MATH  Google Scholar 

  35. Shen J, Kang SH, Chan TF (2003) Euler's Elastica and curvature-based Inpainting. SIAM J Appl Math 63(2):564–592

    Article  MathSciNet  Google Scholar 

  36. Telea A (2004) An image Inpainting technique based on the fast marching method. J Graph Tools 9(1):23–34

    Article  Google Scholar 

  37. Wang H, Jiang L, Liang R, Li XX (2017) Exemplar based image inpainting using structure consistent patch matching. Neurocomputing 269:90–96

    Article  Google Scholar 

  38. Xu Z, Sun J (2010) Image Inpainting by Patch propagation using patch sparsity. IEEE Trans Image Process 19(5):1153–1165

  39. Ying H, Kai L, Ming Y (2017) An improved image Inpainting algorithm based on image segmentation, International Congress of Information and Communication Technology (ICICT)

  40. Zhang M, Desrosiers C (2017) Image completion with global structure and weighted nuclear norm regularization, International Joint Conference on Neural Networks (IJCNN)

  41. Zhang J, Zhao D, Gao W (2014) Group-based sparse representation for image restoration. IEEE Trans Image Process 23(8):3336–3351

    Article  MathSciNet  Google Scholar 

  42. Zhang L et al (2015) Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding. Pattern Recogn 48:3102–3112

    Article  Google Scholar 

  43. Zhang L, Zhang L, Du B, You J, Tao D (2019) Hyperspectral image unsupervised classification by robust manifold matrix factorization. Inf Sci 485:154–169

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Electrical and Computer Engineering Department, Semnan University, Semnan, Iran

    Farzin Yaghmaee & Kimia Peyvandi

Authors
  1. Farzin Yaghmaee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kimia Peyvandi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Farzin Yaghmaee.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yaghmaee, F., Peyvandi, K. Improving image inpainting quality by a new SVD-based decomposition. Multimed Tools Appl 79, 13795–13809 (2020). https://doi.org/10.1007/s11042-020-08650-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-08650-x

Keywords

Search

Navigation