Skip to main content
SpringerLink
Log in

Efficient image colorization based on seed pixel selection

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Colorization is a technique to automatically produce color components for monochrome images and videos based on a few input colors. Generally, image colorization is initialized from a number of seed pixels whose colors are specified by users, and then the colors are gradually prorogating to the monochrome surroundings under a given optimization constraint. So, the performance of colorization is highly dependent on the selection of seed pixels. However, little attention has been paid to the selection of seed pixels, and how to improve the effectiveness of manual input remains a challenging task. To address this, an improved colorization method using seed pixel selection is proposed to assist the users in determining which pixels are highly required to be colorized for a high-quality colorized image. Specifically, the gray-scale image is first divided into non-overlapped blocks, and then, for each block, two pixels that approximate the average luminance of block are selected as the seeds. After the seed pixels are colored by users, an optimization that minimizes the difference between the seeds and their adjacent pixels is employed to propagate the colors to the other pixels. The experimental results demonstrate that, for a given amount of inputs, the proposed method can achieve a higher PSNR than the conventional colorization methods.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Notes

  1. http://homepages.lboro.ac.uk/~cogs/datasets/ucid/ucid.html.

  2. http://sipi.usc.edu/database/database.php?volume=misc.

  3. http://www.r0k.us/graphics/kodak/.

References

  1. An X, Pellacini F (2008) Appprop: all-pairs appearance-space edit propagation. ACM Trans Graph 27(3):15–19

    Article  Google Scholar 

  2. Anagnostopoulos N, Iakovidou C, Amanatiadis A, Boutalis Y, Chatzichristofis S (2014) Two-staged image colorization based on salient contours. In: International Conference on Imaging Systems and Techniques, IEEE, pp 381–385

  3. Balinsky A, Mohammad N Sparse natural image statistics and their applications to colorization and compression. In: International Conference on Image Processing

  4. Bezerra H, Feijó B, Velho L (2006) A computer-assisted colorization algorithm based on topological difference. In: Brazil Ian symposium on computer graphics and image processing, IEEE

  5. Bugeau A, Ta V-T (2012) Patch-based image colorization. In: International Conference on Pattern Recognition, IEEE, pp 3058–3061

  6. Bugeau A, Ta V-T, Papadakis N (2014) Variational exemplar-based image colorization. Trans Image Process 23(1):298–307

    Article  MathSciNet  Google Scholar 

  7. Chaumont M, Puech W (2008) Attack by colorization of a grey-level image hiding its color palette. In: International Conference on Multimedia & Expo, IEEE, pp 1537–1540

  8. Chen X, Zou D, Zhao Q, Tan P (2012) Manifold preserving edit propagation. ACM Trans Graph 31(6):439–445

    Google Scholar 

  9. Chen X, Li J, Zou D, Zhao Q (2016) Learn sparse dictionaries for edit propagation. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society 25(4):1688–1698

    Article  MathSciNet  Google Scholar 

  10. Devi MS, Mandowara A (2012) Extended performance comparison of pixel window size for colorization of grayscale images using yuv color space. In: Nirma University International Conference on Engineering, IEEE, pp 1–5

  11. Drew MS, Finlayson GD (2008) Realistic colorization via the structure tensor. In: International Conference on Image Processing, IEEE, pp 457–460

  12. Du W (2012) Colorization using the information of prototypes and edges. In: International Conference on Intelligent Control and Information Processing, IEEE, pp 644–647

  13. Gondal I, Murshed M et al (2010) Scarf: Semi-automatic colorization and reliable image fusion

  14. Gunel M, Karacan L, Erdem AT, Erdem E (2014) Image colorization via dense correspondences. In: Signal Processing and Communications Applications Conference, IEEE, pp 285–288

  15. Heu J-H, Hyun D-Y, Kim C-S, Lee S-U (2009) Image and video colorization based on prioritized source propagation. In: International Conference on Image Processing, IEEE, pp 465–468

  16. Irony R, Cohen-Or D, Lischinski D (2005) Colorization by example Eurographics symp on rendering, vol. 2, citeseer

    Google Scholar 

  17. Jacob VG, Gupta S (2009) Colorization of grayscale images and videos using a semiautomatic approach. In: International Conference on Image Processing, IEEE, pp 1653–1656

  18. Kawulok M, Smolka B (2010) Competitive image colorization. In: International Conference on Image Processing, IEEE, pp 405–408

  19. Kim TH, Lee KM, Lee SU (2009) Edge-preserving colorization using data-driven random walks with restart. In: International Conference on Image Processing, IEEE, pp 1661–1664

  20. Kumar S, Swarnkar A (2012) Gray image colorization in ycbcr color space. In: International conference on emerging technology trends in electronics, Communication and Networking, IEEE, pp 1–6

  21. Kumar S, Swarnkar A (2012) Colorization of gray scale images in l α β color space using mean and standard deviation. In: Students’ conference on electrical, Electronics and Computer Science, IEEE, pp 1–4

  22. Lee S, Park S-W, Oh P, Kang MG (2013) Colorization-based compression using optimization. Trans Image Process 22(7):2627–2636

    Article  Google Scholar 

  23. Levin A, Lischinski D, Weiss Y (2004) Colorization using optimization. In: Transactions on Graphics, Vol. 23, ACM, pp 689–694

  24. Lezoray O, Ta VT, Elmoataz A (2008) Nonlocal graph regularization for image colorization. In: International Conference on Pattern Recognition, IEEE, pp 1–4

  25. Liu X, Wan L, Qu Y, Wong T-T, Lin S, Leung C-S, Heng P-A (2008) Intrinsic colorization. In: Transactions on Graphics, Vol. 27, ACM, p 152

  26. Luan Q, Wen F, Cohen-Or D, Liang L, Xu Y-Q, Shum H-Y (2007) Natural image colorization. In: Eurographics conference on Rendering Techniques, Eurographics Association, pp 309–320

  27. Nakajima Y, Ueno T, Yoshida T, Ikehara M (2013) Colorization based on piecewise autoregressive model. In: Asilomar conference on signals, Systems and Computers, IEEE, pp 1990–1994

  28. Nie D, Ma Q, Ma L, Xiao S (2007) Optimization based grayscale image colorization. Pattern recognition letters 28(12):1445–1451

    Article  Google Scholar 

  29. Pang J, Au OC, Tang K, Guo Y (2013) Image colorization using sparse representation. In: International conference on acoustics, Speech and Signal Processing, IEEE, pp 1578–1582

  30. Pang J, Au OC, Yamashita Y, Ling Y, Guo Y, Zeng J (2014) Self-similarity-based image colorization. In: International Conference on Image Processing, IEEE, pp 4687–4691

  31. Pellacini F, Lawrence J (2007) Appwand: editing measured materials using appearance-driven optimization. ACM Trans Graph 26(3):54

    Article  Google Scholar 

  32. Pierre F, Aujol J-F, Bugeau A, Papadakis N, Ta V-T (2015) Luminance-chrominance model for image colorization. Journal on Imaging Sciences 8 (1):536–563

    Article  MATH  MathSciNet  Google Scholar 

  33. Rusu C, Tsaftaris S et al (2013) Estimation of scribble placement for painting colorization. In: International Symposium on Image and Signal Processing and Analysis, IEEE, pp 564–569

  34. Ryu T, Wang P, Lee S-H (2013) Image compression with meanshift based inverse colorization. In: International conference on consumer electronics

  35. Sheng B, Sun H, Chen S, Liu X, Wu E (2011) Colorization using the rotation-invariant feature space. Computer Graphics and Applications (2):24–35

  36. Sỳkora D, Buriánek J, žára J (2004) Unsupervised colorization of black-and-white cartoons. In: Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering, ACM, pp 121–127

  37. Thepade SD, Garg RH, Ghewade SA, Jagdale PA, Mahajan NM (2015) Performance assessment of assorted similarity measures in gray image colorization using lbg vector quantization algorithm. In: International Conference on Industrial Instrumentation and Control, IEEE, pp 332–337

  38. Uruma K, Konishi K, Takahashi T, Furukawa T (2014) Image colorization algorithm using series approximated sparse function. In: International conference on acoustics, Speech and Signal Processing, IEEE, pp 1215–1219

  39. Wang H, Gan Z, Zhang Y, Zhu X (2012) Novel colorization method based on correlation neighborhood similarity pixels priori. In: International Conference on Signal Processing, Vol. 2, IEEE, pp 885–888

  40. Wang S, Zhang Z (2012) Colorization by matrix completion. In: AAAI, Citeseer

  41. Welsh T, Ashikhmin M, Mueller K (2002) Transferring color to grayscale images. Transaction on Graphic 21(3):277–280

    Google Scholar 

  42. Xie D-e, Xuan Y, Zhang Z (2010) A colored pencil-drawing generating method based on interactive colorization. In: International Conference on Computing, Control and Industrial Engineering, Vol. 2, IEEE, pp 166–169

  43. Yatziv L, Sapiro G (2006) Fast image and video colorization using chrominance blending. Trans Image Process 15(5):1120–1129

    Article  Google Scholar 

Download references

Acknowledgments

This work is supported by the National Science Foundation of China (Nos. 61502160, 61502158, 61472131, 61572182), the Science and Technology Key Projects of Hunan Province (2015 TP1004), and the Scientific Research Plan of Hunan Provincial Science and Technology Department of China (2014FJ4161).

Author information

Authors and Affiliations

  1. College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China

    Min Hu, Bo Ou & Yi Xiao

Authors
  1. Min Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bo Ou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bo Ou.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, M., Ou, B. & Xiao, Y. Efficient image colorization based on seed pixel selection. Multimed Tools Appl 76, 23567–23588 (2017). https://doi.org/10.1007/s11042-016-4112-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-016-4112-9

Keywords

Search

Navigation