Colorization Using Segmentation with Random Walk

  • Xiaoming Liu
  • Jun Liu
  • Zhilin Feng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)


Traditional monochrome image colorization techniques require considerable user interaction and a lot of time. The segment-based colorization works fast but at the expense of detail loss because of the large segmentation; while the optimization based method looks much more continuous but takes longer time. This paper proposed a novel approach: Segmentation colorization based on random walks, which is a fast segmentation technique and can naturally handle multi-label segmentation problems. It can maintain smoothness almost everywhere except for the sharp discontinuity at the boundaries in the images. Firstly, with the few seeds of pixels set manually scribbled by the user, a global energy is set up according to the spatial information and statistical grayscale information. Then, with random walks, the global optimal segmentation is obtained fast and efficiently. Finally, a banded graph cut based refine procedure is applied to deal with ambiguous regions of the previous segmentation. Several results are shown to demonstrate the effectiveness of the proposed method.


colorization random walks graph cut image segmentation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Anat, L., Dani, L., Yair, W.: Colorization using optimization. ACM Transaction on Graph 23(3), 689–694 (2004)CrossRefGoogle Scholar
  2. 2.
    Sapiro, G.: Inpainting the colors. In: IEEE International Conference on Image Processing, ICIP 2005 vol. 2, pp. 698–701 (2005)Google Scholar
  3. 3.
    Yatziv, L., Sapiro, G.: Fast image and video colorization using chrominance blending. IEEE Transactions on Image Processing 15(5), 1120–1129 (2006)CrossRefGoogle Scholar
  4. 4.
    Suganuma, K., Sugita, J., Takahashi, T.: Colorization using harmonic templates. In: International Conference on Computer Graphics and Interactive Techniques. ACM, New York (2008)Google Scholar
  5. 5.
    Qu, Y., Wong, T.T., Heng, P.A.: Manga colorization. ACM Transactions on Graphics (TOG) 25(3), 1214–1220 (2006)CrossRefGoogle Scholar
  6. 6.
    Horiuchi, T., Hirano, S.: Colorization algorithm for grayscale image by propagating seed pixels. In: 2003 International Conference on Image Processing. IEEE, Los Alamitos (2003)Google Scholar
  7. 7.
    Irony, R., Cohen-Or, D., Lischinski, D.: Colorization by example. In: Proc. of Eurographics Symposium on Rendering 2005 (2005)Google Scholar
  8. 8.
    Dalmau-Cedeno, O., Rivera, M., Mayorga, P.P.: Computing the alpha-Channel with Probabilistic Segmentation for Image Colorization (2007)Google Scholar
  9. 9.
    Grady, L., Funka-Lea, G.: Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials. In: ECCV. Springer, Heidelberg (2004)Google Scholar
  10. 10.
    Grady, L.: Random Walks for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1768–1783 (2006)Google Scholar
  11. 11.
    Grady, L.: Multilabel random walker image segmentation using prior models. In: CVPR (2005)Google Scholar
  12. 12.
    Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Eighth IEEE International Conference on Computer Vision, ICCV 2001, Proceedings. (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Xiaoming Liu
    • 1
  • Jun Liu
    • 1
  • Zhilin Feng
    • 2
  1. 1.College of Computer Science and TechnologyWuhan University of Science and TechnologyWuhanChina
  2. 2.Zhijiang CollegeZhejiang University of TechnologyHangzhouChina

Personalised recommendations