Skip to main content
SpringerLink
Log in

Convolution Formulation of Cost Function in Cohen-Or Color Harmonization

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

The impression of an image changes depending on the combination of colors used, even though the content itself stays the same. Color harmonization is a technique that changes the color distribution of an image to improve the aesthetics of the image. Many methods have therefore been proposed previously. However, the computational cost for color harmonization is often expensive. This is particularly problematic when applying the technique to high-resolution images or videos, such as 4K or 8K images, which are becoming common nowadays. In this paper, we present a fast color harmonization technique to address this problem. We reformulate the cost function for color harmonization so that we can use fast Fourier transforms. Our method achieves two to three orders of magnitudes faster computation than the previous methods. This allows us to harmonize a high-resolution image or video in real time.

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. Krause J. Color Index: Over 1,100 Color Combinations. Arlington: F & W Publication Inc.; 2001.

    Google Scholar 

  2. Itten J. The art of color. New York: Van Nostrand Reinhold Company; 1960.

    Google Scholar 

  3. Meier B. In UIST ’88 Proceedings of the 1st annual ACM SIGGRAPH symposium on User interface software; 1988. pp 117–128.

  4. Cohen-Or D, Sorkine O, Gal R, Leyvand T, Xu YQ. ACM Trans. on Graphics (Proc. SIGGRAPH 2006) 2006;25(3). pp 624.

  5. Matsuda Y. Color design. Tokyo: Asakura Shoten; 1995.

    Google Scholar 

  6. Sawant N, Mitra NJ. Color Harmonization for Video, In Indian conference on computer vision, graphics and image processing; Bhubaneshwar; 2008. pp 576–582.

  7. Huo X, Tan J. An improved method for color harmonization, In Image and Signal Processing. CISP’09. In: 2nd International Congress on IEEE; Tianjin; 2009. pp 1–4.

  8. Gruber L, Kalkofen D, Chmalstieg D. Color harmonization for Augmented Reality, In Proceedings of 2010 IEEE international symposium on mixed and augmented reality Seoul; 2010. pp 227–228.

  9. Tsai YH, Shen X, Lin Z, Sunkavalli K, Lu X, Yang MH. Deep Image Harmonization, In Proceedings of 2017 IEEE conference on computer vision and pattern recognition (CVPR); Honolulu; 2017. pp 2799–2807.

  10. Baveye Y, Urban F, Chamaret C, Demoulin V, Hellier P. Saliency-Guided Consistent Color Harmonization. In: Tominaga S, Schettini R, Trémeau A. (eds) Computational Color Imaging. CCIW 2013. Lecture Notes in Computer Science, Springer, Berlin, Heidelberg; 2013. vol 7786. https://doi.org/10.1007/978-3-642-36700-7_9.

  11. Li X, Zhao H, Nie G, Huang H, Image recoloring using geodesic distance based on color harmonization. Comput Visual Media 2015;1(2):143-155.

  12. Zhen T, Zhenjiang M, Yanli W. Image composition with color harmonization, In 2010 25th international conference of image and vision computing; New Zealand; 2010. pp 1–8. https://doi.org/10.1109/IVCNZ.2010.6148796.

  13. Chamaret C, Urban F, Oisel L. Harmony-guided image editing, In 2014 IEEE international conference on image processing (ICIP); Paris; 2014. pp 2171–2173. https://doi.org/10.1109/ICIP.2014.7025437

  14. Tokumaru M, Muranaka N, Imanishi S. Color design support system considering color harmony, Proceeding sof the IEEE international conference on fuzzy systems; Rio de Janeiro; 2002. pp 378–83.

  15. Press WH, Teukolsky SA, Vetterling WT, Flannery BP. Numerical recipes in C: the art of scientific computing. Cambridge: Cambridge University Press; 1992.

    MATH  Google Scholar 

Download references

Acknowledgements

This work was supported by JSPS KAKENHI Grant nos. JP15H05924, JP19H04196, and JP20H05954.

Author information

Authors and Affiliations

  1. Hokkaido University, Kita-ku, Kita 14, Nishi 9, Sapporo, Japan

    Kento Mannen & Yoshinori Dobashi

Authors
  1. Kento Mannen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yoshinori Dobashi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yoshinori Dobashi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mannen, K., Dobashi, Y. Convolution Formulation of Cost Function in Cohen-Or Color Harmonization. SN COMPUT. SCI. 3, 86 (2022). https://doi.org/10.1007/s42979-021-00969-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-021-00969-y

Keywords

Search

Navigation