Image Colorization Algorithm based on Dense Neural Network

doi:10.23940/ijpe.19.01.p27.270280

Int J Performability Eng ›› 2019, Vol. 15 ›› Issue (1): 270-280.doi: 10.23940/ijpe.19.01.p27.270280

Previous Articles Next Articles

Image Colorization Algorithm based on Dense Neural Network

Na Zhang, Pinle Qin, Jianchao Zeng(), and Yulong Song

School of Data Science and Technology, North University of China, Taiyuan, 030051, China

Revised on ; Accepted on
Contact: Zeng Jianchao E-mail:zjc@nuc.edu.cn
About author:Na Zhang received her undergraduate degree in School of Information and Statistics from Guangxi University of Finance and Economics, Nanning, Guangxi, P.R. China, in 2015. Currently, she is pursuing master’s degree in NUC, and her areas of interest are digital image processing, medical image processing and computer vision.|Pinle Qin received the PhD degree in computer application technology from Dalian University of Technology (DLUT), Dalian, Liaoning, P.R. China, in 2008. He is currently an associate professor with the School of Data Science and Technology, North University of China (NUC). His current research interests include computer vision, medical image processing and deep learning.|Jianchao Zeng received the PhD degree from Xi’an Jiaotong University, Xi’an, Shanxi, P.R. China, in 1990. He is currently the vice president of North University of China (NUC). His current research interests include computer vision, medical image processing and deep learning.|Yulong Song is pursing master`s degree in NUC, and his research areas are digital image processing and computer vision.

Abstract

Abstract:

In most scenes, color images have richer information than grayscale images. This paper presents a method of grayscale image pseudo coloring that constructed and trained an end-to-end deep learning model based on dense neural network aims to extract all kinds of information and features (such as classification information and detail feature information). Entering a grayscale picture to the trained networkcan generate a full and vibrant vivid color picture. By constantly training the entire network on a wide variety of data sets, you will get the most adaptable, high-performance pseudo color network. The experiments show that the method proposed has a higher utilization of features and can obtain a satisfactory coloring effect. Compared with the current advanced pseudo color methods, it has also made remarkable improvements, and to a certain extent, the problem during the coloring processing have been improved, such as color overflow, loss of details, low contrast etc.

Key words: image coloring, densely connected convolutional networks, grayscale image, feature utilization, information loss

Na Zhang, Pinle Qin, Jianchao Zeng, and Yulong Song. Image Colorization Algorithm based on Dense Neural Network [J]. Int J Performability Eng, 2019, 15(1): 270-280.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

Figures/Tables 8

Figure 1

Figure 2

Figure 3

Figure 4

Table 1

Figure 5

Figure 6

Figure 7

References 28

[1]	R. Gonzalez and R. Woods , “Digital Image Processing,” Publishing House of Electronics Industry, Beijing, 2011
[2]	A. Levin, D. Lischinski, and Y. Weiss , “Colorization using Optimization,”ACM SIGGRAPH, Vol. 23, No. 3, pp. 689-694, 2004
[3]	P. Lagodziński and B. Smolka , “Medical Image Colorization,”Journal of Medical Informatics & Technologies, Vol. 11, pp. 47-57, November 2007
[4]	A.A. Shah, M. Gandhi, K. M. Shah , “Medical Image Colorization using Optimization Technique,”Acta Medica Okayama, Vol. 62, No. 141, pp. 235-248, 2013
[5]	F. Li, L. Zhu, L. Zhang, Y. Liu, A. Wang , “Pseudo-Colorization of Medical Images based on Two-Stage Transfer Model,”Chinese Journal of Stereology & Image Analysis, Vol. 18, No. 2, pp. 135-144, February 2013
[6]	T. Welsh, M. Ashikhmin, and K. Mueller , “Transferring Color to Grayscale Images,”Acm Transactions on Graphics, Vol.21, No. 3, pp. 277-280, July 2002
[7]	X. Liu, L. Wan, Y. Qu, T.T. Wong, S. Lin , “Intrinsic Colorization,”Acm Siggraph Asia, Vol. 27, No. 5, pp. 1-9, December 2008
[8]	Y. Liu, C. Michael, U. Matt, R. Szymon , “AutoStyle: Automatic Style Transfer from Image Collections to Users’ Images,”Eurographics Symposium on Rendering Eurographics Association, Vol. 33, No. 4, pp. 21-31, July 2014 doi: 10.1111/cgf.12409
[9]	Y. Morimoto, Y. Taguchi, T. Naemura , “Automatic Colorization of Grayscale Images using Multiple Images on the Web,”inProceedings of the SIGGRAPH 2009: TalksACM, pp. 1-1, New York, USA, August 2009 doi: 10.1145/1599301.1599333
[10]	R. Irony, D. Cohen-Or, D. Lischinski , “Colorization by Example,”Eurographics Symposium on Rendering Techniques, Konstanz, Germany,Vol.5, No. 10, pp. 201-210, June 2005
[11]	Z. Cheng, Q. Yang, B. Sheng , “Deep Colorization,” in Proceedings of the2015 IEEE International Conference on Computer Vision (ICCV), pp. 415-423, Santiago, Chile, December 2015
[12]	A. Deshpande, J. Rock, D. Forsyth , “Learning Large-Scale Automatic Image Colorization,” in Proceedings of the2015 IEEE International Conference on Computer Vision (ICCV), pp. 567-575, Santiago, Chile, 2015 doi: 10.1109/ICCV.2015.72
[13]	R. Zhang, P. Isola, A. A. Efros , “Colorful Image Colorization,”in Proceedings of the European Conference on Computer Vision (ECCV), pp. 649-666, Amsterdam, The Netherlands, October 2016
[14]	K. Simonyan and A. Zisserman , “Very Deep Convolutional Networks for Large-Scale Image Recognition,”arXiv Preprint arXiv: 1409.1556, September 2014
[15]	O. Ronneberger, P. Fischer, T. Brox , “U-Net: Convolutional Networks for Biomedical Image Segmentation,”in Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241, Munich, Germany, October 2015
[16]	R. Zhang, J.Y. Zhu, P. Isola, X. Geng, A. S. Lin, T. Yu , et al., “Real-Time User-Guided Image Colorization with Learned Deep priors,”Acm Transactions on Graphics, Vol. 36, No. 4, pp. 119:1-119:11, July 2017 doi: 10.1145/3072959.3073703
[17]	S. Lizuka, E. Simo-Serra, H. Ishikawa , “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, Vol.35, No. 4, pp. 1-11, July 2016 doi: 10.1145/2897824.2925974
[18]	P. Qin, Z. Cheng, Y. Cui, J. Zhang, Q. Miao , “Research on Image Colorization Algorithm based on Residual Neural Network,” in Proceedings of theCCF Chinese Conference on Computer Vision, pp. 608-621, Tianjin, China, October 2017 doi: 10.1007/978-981-10-7299-4_51
[19]	K. He, X. Zhang, S. Ren, J. Sun , “Deep Residual Learning for Image Recognition,” in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, Las Vegas, USA, June 2016 doi: 10.1109/CVPR.2016.90
[20]	G. Huang, Z. Liu, K.Q. Weinberger , “Densely Connected Convolutional Networks,” in Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ,pp. 1-9, Honolulu, Hawaii, USA, July 2017
[21]	A. Krizhevsky, I. Sutskever, G.E. Hinton , “ImageNet Classification with Deep Convolutional Neural Networks,”in Proceedings of the 25th International Conference on Neural Information Processing Systems, pp. 1097-1105, Nevada, December 2012
[22]	C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov , et al., “Going Deeper with Convolutions,” in Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, Boston, MA, USA, June 2015
[23]	R.K. Srivastava, K. Greff, J. Schmidhuber , “Highway Networks,” arXiv Preprint arXiv:1505.00387, May 2015
[24]	G. Huang, Y. Sun, Z. Liu, D. Sedra, K.Q. Weinberger , “Deep Networks with Stochastic Depth,”in Proceedings of the 2016 European Conference on Computer Vision (ECCV), pp. 646-661, Amsterdam, Netherlands, October 2016
[25]	G. Larsson, M. Maire, G. Shakhnarovich , “FractalNet: Ultra-Deep Neural Networks without Residuals,” arXiv Preprint arXiv:1605.07648, May 2016
[26]	B. Zhou, A. L. Garcia, J. Xiao.A . Torralba,and A. Oliva, “Learning Deep Features for Scene Recognition using Places Database,” in Proceedings of the 27 ^th International Conference onNeural Information Processing Systems, pp . 487-495, Montréal, CANADA, December 2014
[27]	J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, F. Li , “ImageNet: A Large-Scale Hierarchical Image Database,” in Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248-255, Florida, USA, August 2009
[28]	M. Abadi, A. Agarwal, P. Barham. E. Brevdo, and Z.F. Chen, C. Citro, et al., “Tensorflow: Large-Scale Machine Learning on Heterogeneous Distributed Systems,”arXiv Preprint arXiv:1603.04467, March 2016

Image Colorization Algorithm based on Dense Neural Network

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 28

Related Articles 0

Recommended 0