How to use Information Theory for Image Inpainting and Blind Spot Filling-in?

J. M. Berthommé, T. Chateau, M. Dhome

Abstract

This paper shows how information theory can both drive the digital image inpainting process and the optical illusion due to the blind spot. The defended position is that the missing information is padded by the ``most probable information around'' via a simple filling-in scheme. Thus the proposed algorithm aims to keep the entropy constant. It cares not to create too much novelty as well as not to destroy too much information. For this, the image is broken down into regular squares in order to build a dictionary of unique words and to estimate the entropy. Then the occluded region is completed, word by word and layer by layer, by picking the element which respects the existing image, which minimizes the entropy deviation if there are several candidates, and which limits its potential increase in the case where no compatible word exists and where a new one must be introduced.

References

  1. Arias, P., Facciolo, G., Caselles, V., and Sapiro, G. (2011). A variational framework for exemplar-based image inpainting. International journal of computer vision, 93(3):319-347.
  2. Durgin, F. H. (1995). On the filling in of the visual blind spot: some rules of thumb. Perception, 24:827-840.
  3. Kawai, N., Sato, T., and Yokoya, N. (2009). Image inpainting considering brightness change and spatial locality of textures and its evaluation. Advances in Image and Video Technology, pages 271-282.
  4. Liu, D., Sun, X., Wu, F., Li, S., and Zhang, Y. (2007). Image compression with edge-based inpainting. Circuits and Systems for Video Technology, IEEE Transactions on, 17(10):1273-1287.
  5. MacKay, D. (2003). Information Theory, Inference, and Learning Algorithms. Cambridge University Press.
  6. Satoh, S. (2011). Computational identity between digital image inpainting and filling-in process at the blind spot. Neural Computing & Applications, pages 1-9.
Download


Paper Citation


in Harvard Style

Berthommé J., Chateau T. and Dhome M. (2013). How to use Information Theory for Image Inpainting and Blind Spot Filling-in? . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 97-100. DOI: 10.5220/0004216300970100


in Bibtex Style

@conference{visapp13,
author={J. M. Berthommé and T. Chateau and M. Dhome},
title={How to use Information Theory for Image Inpainting and Blind Spot Filling-in?},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={97-100},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004216300970100},
isbn={978-989-8565-47-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - How to use Information Theory for Image Inpainting and Blind Spot Filling-in?
SN - 978-989-8565-47-1
AU - Berthommé J.
AU - Chateau T.
AU - Dhome M.
PY - 2013
SP - 97
EP - 100
DO - 10.5220/0004216300970100