Skip to main content
SpringerLink
Log in

Inpainting images with curvilinear structures propagation

  • Short Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Inpainting images with smooth curvilinear structures interrupted is a challenging problem, because the structures are salient features sensitive to the human vision system and they are not easy to be completed in a visually pleasing way, especially when gaps are large. In this paper, we propose an approach to address this problem. A curve with a desired nice shape is first created to smoothly extend the missing structure from the known to unknown regions. As the curve partitions the unknown region into separate areas, textures can be filled independently into each area. We then adopt a patch-based texture inpainting method enhanced by a novel similarity measurement of patches. After that, very abrupt edges caused by different inpainted colours on their two sides need to be smoothed for natural colour transition across the curve. Experimental results demonstrate the effectiveness of the proposed approach.

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. Chan, T., Shen, J.: Non-texture inpaintings by curvature driven diffusion. J. Vis. Commun. Image Represent. 12(4), 436–449 (2001)

    Article  Google Scholar 

  2. Shih, C., Lai, T., Chu, H., Chen, Y.: Image completion using prediction concept via support vector regression. Mach. Vis. Appl. 24(4), 753–768 (2013)

    Article  Google Scholar 

  3. Drori, I., Cohen-or, D., Yeshurun, H.: Fragment-based image completion. ACM Trans. Graph. 22(3), 303–312 (2003)

  4. Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)

    Article  Google Scholar 

  5. Bertalmio, M., Vese, L., Sapiro, G., Osher, S.: Simultaneous structure and texture image inpainting. IEEE Trans. Image Process. 12(8), 882–889 (2003)

    Article  Google Scholar 

  6. Shen, J., Jin, X., Zhou, C.: Gradient based image completion by solving the Poisson equation. Comput. Graph. 31(1), 119–126 (2007)

    Article  Google Scholar 

  7. Jia, J., Tang, C.: Image repairing: robust image synthesis by adaptive ND tensor voting. In: CVPR, pp. 1643–1650 (2003)

  8. Wu, J., Ruan, Q.: Object removal by cross isophotes exemplar-based inpainting. In: ICPR (2006)

  9. Komodakis, N., Tziritas, G.: Image completion using global optimization. CVPR 1, 442–452 (2006)

    Google Scholar 

  10. Huang, T., Chen, S., Liu, J., Tang, X.: Image inpainting by global structure and texture propagation. In: ACM MM, pp. 517–520 (2007)

  11. Sun J., Yuan L., Jia J., Shum, H.: Image completion with structure propagation. In: SIGGRAPH, pp. 861–868 (2005)

  12. Hung, J., Huang, C., Liao, Y., Tang, N., Chen, T.: Examplar-based image inpainting based on structure construction. J. Softw. 3(8), 57–64 (2008)

    Google Scholar 

  13. Harary, G., Tal, A.: 3D Euler spirals for 3D curve completion. In: ACM SoCG, pp. 393–402 (2010)

  14. Horn, B.: The curve of least energy. ACM Trans. Math. Softw. 9(4), 442–460 (1983)

    Article  MathSciNet  Google Scholar 

  15. Ullman, S.: Filling-in the gaps: the shape of subjective contours and a model for their generation. Biol. Cybern. 25(1), 1–6 (1976)

    MathSciNet  Google Scholar 

  16. Kimia, B., Frankel, I., Popescu, A.: Euler spiral for shape completion. IJCV 54(1), 159–182 (2003)

    MATH  Google Scholar 

  17. Zhou, H., Zheng, J., Yang, X.: Euler arc splines for curve completion. Comput. Graph. 36(6), 642–650 (2012)

    Article  Google Scholar 

  18. Fidaner, I.: A survey on variational image inpainting, texture synthesis and image completion. (2008). http://issuu.com/fidaner/docs/3012627-a-survey-on-variational-image-inpainting-t. Accessed Aug 2014

  19. Zhou H., Zheng, J.: Adaptive patch size determination for patch-based image completion. In: ICIP, pp. 421–424 (2010)

  20. Perez, P., Gangnet, M., Blake, A.: Poisson image editing. In: SIGGRAPH, pp. 313–318 (2003)

  21. Leventhal, D., Gordon, B., Sibley, P.: Poisson image editing extended. In: SIGGRAPH Research Posters, pp. 313–318 (2006)

  22. Yang, W., Zheng, J., Cai, J., Rahardji, S., Chen, C.: Natural and seamless image composition with color control. IEEE Trans. Image Process. 18(11), 2584–2592 (2009)

    Article  MathSciNet  Google Scholar 

  23. Shibata, T., Iketani A., Senda, S.: Fast and structure-preserving inpainting based on probabilistic structure estimation. In: Proc. of Mach. Vis. Appl. (2011)

Download references

Acknowledgments

This work is supported by Centre for Intelligent Systems Research (CISR), Victoria, Australia.

Author information

Authors and Affiliations

  1. Centre for Intelligent Systems Research (CISR), Victoria, Australia

    Hailing Zhou, Lei Wei, Douglas Creighton & Saeid Nahavandi

Authors
  1. Hailing Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lei Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Douglas Creighton
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Saeid Nahavandi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hailing Zhou.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, H., Wei, L., Creighton, D. et al. Inpainting images with curvilinear structures propagation. Machine Vision and Applications 25, 2003–2008 (2014). https://doi.org/10.1007/s00138-014-0635-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-014-0635-0

Keywords

Search

Navigation