A Gaussian Graphical Model Based Approach for Image Inpainting

Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 166)


Digital image inpainting means reconstruction of small damaged portions of images. In this paper, we propose an algorithm for digital image inpainting which is a combination of pixel-diffusing technique and a user interaction mechanism. In our approach, the user manually specifies important missing structure information by extending a few curves or line segments from the known region to the unknown regions. Our approach synthesizes image patches along these user-specified curves in the unknown region using patches selected around the curves in the known region. We call this step as structure propagation. After completing structure propagation, we fill in the remaining unknown regions using Gaussian Graphical Model which is MRF based. The experiment results show that our approach is reasonable and efficient. In addition, our method is very simple to be implemented and fast.


GGM MRF Structure propagation Image inpainting 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Marcelo, B., Guillermo, S., Vicent, C., Coloma, B.: Image Inpainting. In: Proceeding of the ACM SIGGRAPH 2000, New Orleans, pp. 417–424 (2000)Google Scholar
  2. 2.
    Jian, S., Lu, Y., Jiaya, J., Heung, Y.S.: Image completion with structure propagation. ACM Trans. Graph. 24(3), 861–868 (2005)CrossRefGoogle Scholar
  3. 3.
    Antonio, C., Patrick, P., Kentaro, T.: Region filling and object removal by exemplar-based image inpainting. IEEE Transaction on Image Processing 13(9), 1200–1212 (2004)CrossRefGoogle Scholar
  4. 4.
    Haluk, D., Howard, E., Roberto, C., Donald, G.: Bayes smoothing algorithms for segmentation of binary images modeled by Markov random fields. IEEE Trans. Pattern Anal. Mach. Intell. 6, 707–720 (1984)MATHGoogle Scholar
  5. 5.
    Takahiro, O., Miki, H., Hideo, K.: Restoration Method of Missing Areas in Still Images Using GMRF Model. In: International Symposium on IEEE, pp. 931–4934 (2005)Google Scholar
  6. 6.
    Rui, W., Dongbing, G., Guangwen, L., Junxi, S.: A multi-scale image inpainting algorithm based on GMRF model. In: IEEE International Conference on Robotics and Biomimetics (ROBIO), December 19-23, pp. 1844–1848 (2009)Google Scholar
  7. 7.
    Yasuda, M., Ohkubo, J., Tanaka, K.: Digital Image Inpainting based on Markov Random Field. In: International Conference on Intelligent Agents, Web Technologies and Internet Commerce and International Conference on Computational Intelligence for Modelling, Control and Automation, November 28-30, vol. 2, pp. 747–752 (2005)Google Scholar
  8. 8.
    Junxi, S., Defang, H., Dongbing, G., Guangwen, L., Hua, C.: An interactive image inpainting algorithm based on Markov Random Field. In: International Conference on Mechatronics and Automation, ICMA 2009, August 9-12, pp. 101–106 (2009)Google Scholar
  9. 9.
    Jae, S.L.: Two-Dimensional Signal and Image Processing. Prentice Hall PTR (1990)Google Scholar
  10. 10.
    Kazuyuki, T.: Statistical-mechanical approach to image processing. J. Phys. A: Math. Gen. 35, 81–150 (2002)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Department of Computer EngineeringSardar Vallabhbai National Institute of TechnologySuratIndia

Personalised recommendations