Skip to main content

Advertisement

SpringerLink
Log in

Computational identity between digital image inpainting and filling-in process at the blind spot

  • ICONIP2010
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Digital image inpainting (DII) is a computer algorithm that restores missing information of images such as those of old oil paintings. This problem occurs in human visual systems as well: we have blind spots (BS), but we see natural patterns in the BS region. This article presents the computational identity between the DII algorithm and the vision model for the filling-in process at the BS. Based on physiological evidence and conjecture, we define an evaluation function that evaluates the quality of filled-in (or inpainted) images. The definition of the evaluation function helps the original DII algorithm to improve the convergence speed. Numerical experiments demonstrate that the convergence speed using the energy function is three times faster than the original DII algorithm. Results show that the resultant filled-in patterns by the visual model are comparable with those of the DII algorithm.

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

Similar content being viewed by others

References

  1. Grzybowski A, Aydin P (2007) Edme Mariotte (1620–1684): pioneer of neurophysiology. Surv Ophthalmol 52(4):443–451

    Article  Google Scholar 

  2. Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. Proc SIGGRAPH 2000:417–424

    Google Scholar 

  3. Komatsu H (2006) The neural mechanisms of perceptual filling-in. Nat Rev Neurosci 7:200–231

    Article  MathSciNet  Google Scholar 

  4. Matsumoto M, Komatsu H (2005) Neural responses in the Macaque V1 to bar stimuli with various lengths presented on the blind spot. J Neurophys 93(5):2374–2387

    Article  Google Scholar 

  5. Satoh S, Usui S (2008) Computational theory and applications of a filling-in process at the blind spot. Neural Netw 21:1261–1271

    Article  Google Scholar 

  6. Perona P, Malik J (1990) Scale–space and edge detection using anisotropic diffusion. IEEE PAMI 12:629–639

    Article  Google Scholar 

  7. Ito M, Komatsu H (2004) Representation of Angles embedded within contour stimuli in area V2 of Macaque monkeys. J Neurosci 24(13):3313–3324

    Article  Google Scholar 

  8. Poggio T, Torre V, Koch C (1985) Computational vision and regularization theory. Nature 317:314–319

    Article  Google Scholar 

  9. Florack L, Romeny B, Koenderink J, Viergever M (1992) Scale and the differential structure of images. Image Vis Comput 10(6):376–388

    Article  Google Scholar 

  10. Lindeberg T (1994) Scale–space theory in computer vision. Kluwer, The Netherlands

    Google Scholar 

  11. Polak E (1971) Computational methods in optimization. Academic Press, New York

    Google Scholar 

Download references

Acknowledgments

This work was partially supported by a Grant-in-Aid for Young Scientists (#20700279) from the Ministry of Education, Culture, Sports, Science and Technology, Japan.

Author information

Authors and Affiliations

  1. Graduate School of Information Systems, The University of Electro-communications, Chofu, Tokyo, 182-8585, Japan

    Shunji Satoh

Authors
  1. Shunji Satoh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shunji Satoh.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Satoh, S. Computational identity between digital image inpainting and filling-in process at the blind spot. Neural Comput & Applic 21, 613–621 (2012). https://doi.org/10.1007/s00521-011-0646-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-011-0646-y

Keywords

Search

Navigation