Contextual Information Based Facial Image Colorization

Yin Junjie

doi:doi:

| Peer-Reviewed

Contextual Information Based Facial Image Colorization

Yin Junjie

Published in Asia-Pacific Journal of Mathematics and Statistics (Volume 1, Issue 3)

Received: 3 September 2019 Accepted: 14 November 2019 Published: 27 November 2019

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Given no prior knowledge, the process of converting from a grayscale image to a colorful image is an “ill-posed” problem. Most of the previous methods are based on convolutional neural network (CNN), sparse dictionary and user intervention, making colorization either at a huge cost or an arduous work. This paper aims at solving some of the deficiency in previous work, such as methods based on user-intervention require too many human resources, and methods based on machine learning cost too much computational expense. Motivated by this, a novel automatic face image colorization method based on contextual information is proposed by this paper. Our facial image colorization method is based on machine learning. Utilizing the strong correlation between grayscale lightness, texture and color, we first train a joint distribution from our training set, and then solve the color of a targeted grayscale image under multiple constraints including first-order LBP, Second-order LBP, and lightness. Several experiments were performed to show that the proposed method outperforms the previous approaches by offering better authenticity and naturalness. Aiming specifically at facial image colorization, our method manages to achieve convincing results under a relatively small amount of data resources. As a result, this paper achieve desired effect by applying the local binary pattern (LBP) in the field of colorization, and hopefully could be applied in the field of image processing.

Published in	Asia-Pacific Journal of Mathematics and Statistics (Volume 1, Issue 3)
Page(s)	26-43
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Image Generation, Colorization, Contextual Information, LBP (Local Binary Pattern), Nearby-LBP

References

[1]	Levin, A., Lischinski, D., & Weiss, Y. (2004, August). Colorization using optimization. In ACM transactions on graphics (tog) (Vol. 23, No. 3, pp. 689-694). ACM.
[2]	Di Blasi, G., & Reforgiato, D. (2003). Fast colorization of gray images. Eurographics Italian.
[3]	Luan, Q., Wen, F., Cohen-Or, D., Liang, L., Xu, Y. Q., & Shum, H. Y. (2007, June). Natural image colorization. In Proceedings of the 18th Eurographics conference on Rendering Techniques (pp. 309-320). Eurographics Association.
[4]	Zhang, R., Isola, P., & Efros, A. A. (2016, October). Colorful image colorization. In European Conference on Computer Vision (pp. 649-666). Springer, Cham.
[5]	Iizuka, S., Simo-Serra, E., & Ishikawa, H. (2016). Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Transactions on Graphics (TOG), 35(4), 110.
[6]	Deshpande, A., Rock, J., & Forsyth, D. (2015). Learning large-scale automatic image colorization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 567-575).
[7]	Liu, S., & Zhang, X. (2012). Automatic grayscale image colorization using histogram regression(Tech.). Tianjin University. doi:1673-1681
[8]	Kumar, T., & Verma, K. (2010). A Theory Based on Conversion of RGB image to Gray image. International Journal of Computer Applications, 7 (2), 7-10.
[9]	Yan, D., Bai, L., Zhang, Y., & Han, J. (2018). Multi-sparse dictionary colorization algorithm based on the feature classification and detail enhancement. Optical Review, 25(1), 78-93.
[10]	Hao, K. (2012). 基于稀疏编码的图像视觉特征提取及应用 (Y2060075, Tech.). The Hebrew University of Jerusalem. 硕士毕业论文
[11]	Lloyd, J. (2017, May 05). The Process. Retrieved from http://dynamichrome.com/process/,2018/7/25
[12]	K. (n.d.). Famous Black and White Photos Restored in Color. Retrieved from https://www.amusingplanet.com/2012/05/famous-black-and-white-photos-restored.html#modal-one ,2018/8/3
[13]	Welsh, Tomihisa, Michael Ashikhmin, and Klaus Mueller. "Transferring color to greyscale images." ACM Transactions on Graphics (TOG). Vol. 21. No. 3. ACM, 2002.
[14]	Pietikäinen, Matti. "Local binary patterns." Scholarpedia 5.3 (2010): 9775.
[15]	Lloyd, Jordan. “The Hoover Dam Under Construction, 1935.” Medium, Dynamichrome Viewfinder, 5 Apr. 2016, https://medium.com/dynamichrome-viewfinder/the-hoover-dam-under-construction-1935-2148d2ba26d3.

Cite This Article

Plain Text BibTeX RIS

APA Style

Yin Junjie. (2019). Contextual Information Based Facial Image Colorization. Asia-Pacific Journal of Mathematics and Statistics, 1(3), 26-43.

Copy | Download

ACS Style

Yin Junjie. Contextual Information Based Facial Image Colorization. Asia-Pac. J. Math. Stat. 2019, 1(3), 26-43.

Copy | Download

AMA Style

Yin Junjie. Contextual Information Based Facial Image Colorization. Asia-Pac J Math Stat. 2019;1(3):26-43.

Copy | Download

@article{10042844,
  author = {Yin Junjie},
  title = {Contextual Information Based Facial Image Colorization},
  journal = {Asia-Pacific Journal of Mathematics and Statistics},
  volume = {1},
  number = {3},
  pages = {26-43},
  url = {https://www.sciencepublishinggroup.com/article/10042844},
  abstract = {Given no prior knowledge, the process of converting from a grayscale image to a colorful image is an “ill-posed” problem. Most of the previous methods are based on convolutional neural network (CNN), sparse dictionary and user intervention, making colorization either at a huge cost or an arduous work. This paper aims at solving some of the deficiency in previous work, such as methods based on user-intervention require too many human resources, and methods based on machine learning cost too much computational expense. Motivated by this, a novel automatic face image colorization method based on contextual information is proposed by this paper. Our facial image colorization method is based on machine learning. Utilizing the strong correlation between grayscale lightness, texture and color, we first train a joint distribution from our training set, and then solve the color of a targeted grayscale image under multiple constraints including first-order LBP, Second-order LBP, and lightness. Several experiments were performed to show that the proposed method outperforms the previous approaches by offering better authenticity and naturalness. Aiming specifically at facial image colorization, our method manages to achieve convincing results under a relatively small amount of data resources. As a result, this paper achieve desired effect by applying the local binary pattern (LBP) in the field of colorization, and hopefully could be applied in the field of image processing.},
 year = {2019}
}

Copy | Download

TY  - JOUR
T1  - Contextual Information Based Facial Image Colorization
AU  - Yin Junjie
Y1  - 2019/11/27
PY  - 2019
T2  - Asia-Pacific Journal of Mathematics and Statistics
JF  - Asia-Pacific Journal of Mathematics and Statistics
JO  - Asia-Pacific Journal of Mathematics and Statistics
SP  - 26
EP  - 43
PB  - Science Publishing Group
UR  - http://www.sciencepg.com/article/10042844
AB  - Given no prior knowledge, the process of converting from a grayscale image to a colorful image is an “ill-posed” problem. Most of the previous methods are based on convolutional neural network (CNN), sparse dictionary and user intervention, making colorization either at a huge cost or an arduous work. This paper aims at solving some of the deficiency in previous work, such as methods based on user-intervention require too many human resources, and methods based on machine learning cost too much computational expense. Motivated by this, a novel automatic face image colorization method based on contextual information is proposed by this paper. Our facial image colorization method is based on machine learning. Utilizing the strong correlation between grayscale lightness, texture and color, we first train a joint distribution from our training set, and then solve the color of a targeted grayscale image under multiple constraints including first-order LBP, Second-order LBP, and lightness. Several experiments were performed to show that the proposed method outperforms the previous approaches by offering better authenticity and naturalness. Aiming specifically at facial image colorization, our method manages to achieve convincing results under a relatively small amount of data resources. As a result, this paper achieve desired effect by applying the local binary pattern (LBP) in the field of colorization, and hopefully could be applied in the field of image processing.
VL  - 1
IS  - 3
ER  -

Copy | Download

Author Information

Yin Junjie

Guangdong Country Garden School, Guangzhou, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Yin Junjie. (2019). Contextual Information Based Facial Image Colorization. Asia-Pacific Journal of Mathematics and Statistics, 1(3), 26-43.

Copy | Download

ACS Style

Yin Junjie. Contextual Information Based Facial Image Colorization. Asia-Pac. J. Math. Stat. 2019, 1(3), 26-43.

Copy | Download

AMA Style

Yin Junjie. Contextual Information Based Facial Image Colorization. Asia-Pac J Math Stat. 2019;1(3):26-43.

Copy | Download

@article{10042844,
  author = {Yin Junjie},
  title = {Contextual Information Based Facial Image Colorization},
  journal = {Asia-Pacific Journal of Mathematics and Statistics},
  volume = {1},
  number = {3},
  pages = {26-43},
  url = {https://www.sciencepublishinggroup.com/article/10042844},
  abstract = {Given no prior knowledge, the process of converting from a grayscale image to a colorful image is an “ill-posed” problem. Most of the previous methods are based on convolutional neural network (CNN), sparse dictionary and user intervention, making colorization either at a huge cost or an arduous work. This paper aims at solving some of the deficiency in previous work, such as methods based on user-intervention require too many human resources, and methods based on machine learning cost too much computational expense. Motivated by this, a novel automatic face image colorization method based on contextual information is proposed by this paper. Our facial image colorization method is based on machine learning. Utilizing the strong correlation between grayscale lightness, texture and color, we first train a joint distribution from our training set, and then solve the color of a targeted grayscale image under multiple constraints including first-order LBP, Second-order LBP, and lightness. Several experiments were performed to show that the proposed method outperforms the previous approaches by offering better authenticity and naturalness. Aiming specifically at facial image colorization, our method manages to achieve convincing results under a relatively small amount of data resources. As a result, this paper achieve desired effect by applying the local binary pattern (LBP) in the field of colorization, and hopefully could be applied in the field of image processing.},
 year = {2019}
}

Copy | Download

TY  - JOUR
T1  - Contextual Information Based Facial Image Colorization
AU  - Yin Junjie
Y1  - 2019/11/27
PY  - 2019
T2  - Asia-Pacific Journal of Mathematics and Statistics
JF  - Asia-Pacific Journal of Mathematics and Statistics
JO  - Asia-Pacific Journal of Mathematics and Statistics
SP  - 26
EP  - 43
PB  - Science Publishing Group
UR  - http://www.sciencepg.com/article/10042844
AB  - Given no prior knowledge, the process of converting from a grayscale image to a colorful image is an “ill-posed” problem. Most of the previous methods are based on convolutional neural network (CNN), sparse dictionary and user intervention, making colorization either at a huge cost or an arduous work. This paper aims at solving some of the deficiency in previous work, such as methods based on user-intervention require too many human resources, and methods based on machine learning cost too much computational expense. Motivated by this, a novel automatic face image colorization method based on contextual information is proposed by this paper. Our facial image colorization method is based on machine learning. Utilizing the strong correlation between grayscale lightness, texture and color, we first train a joint distribution from our training set, and then solve the color of a targeted grayscale image under multiple constraints including first-order LBP, Second-order LBP, and lightness. Several experiments were performed to show that the proposed method outperforms the previous approaches by offering better authenticity and naturalness. Aiming specifically at facial image colorization, our method manages to achieve convincing results under a relatively small amount of data resources. As a result, this paper achieve desired effect by applying the local binary pattern (LBP) in the field of colorization, and hopefully could be applied in the field of image processing.
VL  - 1
IS  - 3
ER  -

Copy | Download