Colorization by Landmark Pixels Extraction

  • Weiwei Du
  • Shiya Mori
  • Nobuyuki Nakamori
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7088)

Abstract

A one-dimensional luminance scalar is replaced by a vector of a colorful multi-dimension for every pixel of a monochrome image, it is called as colorization. Obviously, it is under-constrained. Some prior knowledge is considered to be given to the monochrome image. Colorization using optimization algorithm is an effective algorithm for the above problem. Scribbles are considered as the prior knowledge. However, it cannot effectively do with complex images without repeating experiments for confirming the place of scribbles. Therefore, in our paper, landmark pixels are considered as the prior knowledge. We propose an algorithm which is colorization by landmark pixels extraction. It need not repeat experiments and automatically generates landmark pixels like scribbles. Finally, colorize the monochrome image according to requirements of user.

Keywords

Colorization A monochrome image Landmark pixels extraction 

References

  1. 1.
    Welsh, T., Ashikhimin, M., Mueller, K.: Transferring color to greyscale images. ACM Transactions on Graphics 21(3), 277–280 (2002)CrossRefGoogle Scholar
  2. 2.
    Levin, A., Lischinski, D., Weiss, Y.: MVA Conference: Colorization using optimization. In: Proceedings of ACM SIGGRAPH 2004, pp. 689–694 (2004)Google Scholar
  3. 3.
    Jack, K.: Video demystified, 3rd edn. Elsevier Science and Technology (2001)Google Scholar
  4. 4.
    Ward, J.H.: Hierarchical grouping to optimize an objective function. Journal of the American Statistical Association 58, 236–244 (1963)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Huang, T.W., Chen, H.T.: Landmark-Based Sparse Color Representation for Color Transfer. In: The 12th IEEE International Conference on Computer Vision, pp.199–204 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Weiwei Du
    • 1
  • Shiya Mori
    • 1
  • Nobuyuki Nakamori
    • 1
  1. 1.Information ScienceKyoto Institute of TechnologyKyotoJapan

Personalised recommendations