Abstract
Image colorization is the process of assigning different RGB values to each pixel of a given grayscale image to obtain the corresponding colorized image. In this work, we propose a new automatic image colorization method based on the modified cycle-consistent generative adversarial network (CycleGAN). This method can generate a natural color image with only one given gray image without reference image or manual interaction. In the proposed method, we first modify the original network structure by combining a u-shaped network with a skip connection to improve the ability of feature representation in image colorization. Meanwhile, we design a compounded loss function to measure the errors between the ground-truth image and the predicted result to improve the authenticity and naturalness of the colorized image; further, we also add the detail loss function to ensure that the details of the generated color and grayscale images are substantially similar. Finally, the performance of the proposed model is verified on different datasets. Experiments show that our method can generate more realistic color images when compared to other methods.
Similar content being viewed by others
References
Attique M, Gilanie G, Ullah H et al (2012) Colorization and Automated Segmentation of Human T2 MR Brain Images for Characterization of Soft Tissues. PLOS ONE 7:e33616
Aquino G, De Jesus Rubio J, Pacheco J et al (2020) Novel Nonlinear Hypothesis for the Delta Parallel Robot Modeling. IEEE Access 8(1):46324–46334
Bahng H, Yoo S, Cho W et al, Bahng H et al (2018) Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation., European Conference on Computer Vision (ECCV), Munich
Bi Z, Yu L, Gao H et al (2020) Improved VGG model-based efficient traffic sign recognition for safe driving in 5G scenarios International Journal of Machine Learning and Cybernetics
Chai C, Liao J, Zou N et al (2018) A one-to-many conditional generative adversarial network framework for multiple image-to-image translations. Multimed Tools Appl 77:22339–22366. https://doi.org/10.1007/s11042-018-5968-7
Cao Y, Zhou Z, Zhang W et al (2017) Unsupervised Diverse Colorization via Generative Adversarial Networks. Lect Notes Comput Sci (LNCS) 10534:151–166
Chang HW, Fried O, Liu YM et al (2015) Palette-based Photo Recoloring. ACM Trans Graph 34(139):10017. New York
Chen J, Ying H, Liu X, Gu J, Feng R, Chen T, Wu JA (2020) Transfer Learning Based Super-Resolution Microscopy for Biopsy Slice Images: The Joint Methods Perspective. IEEE/ACM Transactions on Computational Biology and Bioinformatics
Cheng ZZ, Yang Q, Sheng B (2015) Deep Colorization. IEEE International Conference on Computer Vision (ICCV), pp 415–423
Chiang HS, Chen MY, Huang YJ (2019) Wavelet-Based EEG Processing for Epilepsy Detection Using Fuzzy Entropy and Associative Petri Net. IEEE Access 7:103255-103262
De Jesus R (2009) J SOFMLS: online self-organizing fuzzy modified least-squares network. IEEE Trans Fuzzy Syst 17(6):1296–1309
Elias I, De J, de Jesus Rubio J et al (2020) Genetic Algorithm with Radial Basis Mapping Network for the Electricity Consumption Modeling. Appl Sci 10(12):4239
Fan GF, Qing S, Wang H et al (2013) Support vector regression model based on empirical mode decomposition and auto regression for electric load forecasting. Energies 6(4):1887–1901
Fan GF, Peng LL, Hong WC et al (2016) Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing 173:958–970
Fan GF, Wei X, Li YT et al (2020) Forecasting electricity consumption using a novel hybrid model. Sustain Cit Soc 61:102320
Fan GF, Guo YH, Zheng JM et al (2020) A generalized regression model based on hybrid empirical mode decomposition and support vector regression with back propagation neural network for mid-short term load forecasting. J Forecast 39(5):737–756
Fatima A, Hussain W, Rasool S (2020) Grey is the new RGB: How good is GAN-based image colorization for image compression? Multimed Tools Appl
Fang L, Wang J, Lu G et al (2019) Hand-drawn grayscale image colorful colorization based on natural image. Vis Comput 35:1667–1681
Fang FM, Wang TT, Zeng TY et al (2019) A Superpixel-based Variational Model for Image Colorization IEEE Transactions on Visualization and Computer Graphics (Early Access)
Furusawa C, Hiroshiba K, Ogaki K et al (2017) Comicolorization: Semi-Automatic Manga Colorization. ACM SIGGRAPH Asia
Goodfellow IJ, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. International Conference on Neural Information Processing Systems, pp 2672–2680
Hettiarachchi R, Peters JF (2017) Vorono? region-based adaptive unsupervised color image segmentation. Pattern Recogn 65:119–135
He MC, Gu XJ, Gu XS (2014) A Fast Colorization Algorithm for Infrared Video. Commun Comput Inf Sci 462:282–292
He M, Chen D, Liao J et al (2018) Deep exemplar-based colorization. ACM Transactions on Graphics
Hernandez G, Zamora E, Sossa H et al (2020) Hybrid neural networks for big data classification. Neurocomputing 390:327–340
Ioan V, Lacramioara ST, Mihaela CV (2015) Client-side Medical Image Colorization in a Collaborative Environment. Stud Health Technol Inf 210:904–908
Isola P, Zhu JY, Zhou T et al (2017) Image-to-Image Translation with Conditional Adversarial Networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1125–1134
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 Trans Graph 35:4
Iizuka SA, Simoserra E (2019) DeepRemaster: Temporal Source−Reference Attention Networks for Comprehensive Video Enhancement. SIGGRAPH Asia, BCEC, Brisbane
Johari MM, Behroozi H (2020) Context-aware colorization of gray-scale images utilizing a cycle-consistent generative adversarial network architecture. Neurocomputing 407:94–104
Larsson G, Maire M, Shakhnarovich G (2016) Learning Representations for Automatic Colorization. European Conference on Computer Vision (ECCV), pp 577–593
Lei CY, Chen QF (2019) Fully Automatic Video Colorization with Self-Regularization and Diversity. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach
Lin B, Deng S, Gao H, Yin J (2020) A Multi-Scale Activity Transition Network for Data Translation in EEG Signals Decoding. IEEE/ACM Transactions on Computational Biology and Bioinformatics
Lin J, Song X, Gan T et al (2020) PaintNet: A shape-constrained generative framework for generating clothing from fashion model. Multimed Tools Appl
Liu H, Fu ZL, Han JG et al (2018) Single satellite imagery simultaneous super-resolution and colorization using multi-task deep neural networks. J Vis Commun Image Represent 53:20–30
Liu SF, Zhong GY, Mello SD et al (2018) Switchable Temporal Propagation Network. European Conference on Computer Vision (ECCV), pp 87–102
Mathieu G, Luiz Gustavo R, Gregoire M (2019) Analogue based colorization of remote sensing images using textural information. ISPRS J Photogramm Remote Sens 147:242–254
Meda-Campa?a JA (2018) On the Estimation and Control of Nonlinear Systems With Parametric Uncertainties and Noisy Outputs. IEEE Access 6:31968–31973
Messaou S, Forsyth D, Schwing AG (2018) Structural Consistency and Controllability for Diverse Colorization European Conference on Computer Vision (ECCV)
Patricia LS, Angel DS, Boris XV et al (2018) Near InfraRed Imagery Colorization. IEEE International Conference on Image Processing (ICIP), Athens, pp 2237–2241
Sangkloy P, Lu J, Fang C et al (2017) Scribbler: Controlling Deep Image Synthesis with Sketch and Color. IEEE Conf Comput Vis Pattern Recogn (CVPR) 1:6836–6845
Suarez PL, Sappa AD, Vintimilla BX (2017) Infrared Image Colorization Based on a Triplet DCGAN Architecture. Comput Vis Pattern Recogn Workshops 1:212–217
Suarez PL, Sappa AD, Vintimilla BX (2017) Learning to Colorize Infrared Images. International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS), pp 164–172
Sykora D, Dingliana J, Collins S (2010) Lazybrush: Flexible painting tool for hand-drawn cartoons. Comput Graph Forum 28(2):599–608
Tylecek R, Sara R (2013) Spatial Pattern Templates for Recognition of Objects with Regular Structure Pattern Recognition. Springer, Berlin
Vondrick C, Shrivastava A, Fathi A et al (2018) Tracking Emerges by Colorizing Videos. European Conference on Computer Vision (ECCV), pp 391–408
Wu M, Jin X, Jiang Q et al (2020) Remote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space. Vis Comput
Wu XD, Hoi SCH (2020) Recent advances in deep learning for object detection. Neurocomputing 396:39–64
Xian W, Sangkloy P, Agrawal V et al (2018) TextureGAN: Controlling deep image synthesis with texture patches. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 8456–8465
Xiao C, Han C, Zhang Z et al (2019) Example-based Colourization via Dense Encoding Pyramids Computer Graphics Forum
Yi X, Zhou P, Zheng Y (2019) Interactive Deep Colorization Using Simultaneous Global and Local Inputs. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Zhang R, Isola P, Efros AA (2016) Colorful Image Colorization. European Conference on Computer Vision (ECCV), pp 649–666
Zhang R, Zhu JY, Isola P et al (2017) Real-time user-guided image colorization with learned deep priors. ACM Trans Graph 36:119
Zhang LM, Ji Y, Lin X (2017) Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN. Asian Conference on Pattern Recognition (ACPR)
Zhang W, Fang CW, Li GB (2017) Automatic Colorization with Improved Spatial Coherence and Boundary Localization. J Comput Sci Technol 32 (3):494–506
Zhang L, Li C, Wong TT et al (2018) Two-stage sketch colorization. ACM Transactions on Graphics
Zhang B, He MM, Liao J et al (2019) Deep Exemplar−based Video Colorization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach
Zou X, Wang Z, Li Q et al (2019) Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification. Neurocomputing 367:39–45
Zhang Z, Hong WC (2019) Electric load forecasting by complete ensemble empirical model decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm. Nonlinear Dyn 98:1107–1136
Zhang Z, Ding S, Sun Y (2020) A support vector regression model hybridized with chaotic krill herd algorithm and empirical mode decomposition for regression task. Neurocomputing 410:185–201
Zhu JY, Park T, Isola P et al (2017) Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. IEEE International Conference on Computer Vision (ICCV), pp 2242–2251
Acknowledgements
This research was funded by the National Natural Science Foundation of China (No. 62002313, 61863036), China Postdoctoral Science Foundation (2020T130564, 2019M653507), Key Areas Research Program of Yunnan Province in China (202001BB050076), the Open Foundation of Key Laboratory in Software Engineering of Yunnan Province under Grant No. 2020SE408 and Postdoctoral Science Foundation of Yunnan Province in China.
Author information
Authors and Affiliations
Corresponding author
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
About this article
Cite this article
Huang, S., Jin, X., Jiang, Q. et al. A fully-automatic image colorization scheme using improved CycleGAN with skip connections. Multimed Tools Appl 80, 26465–26492 (2021). https://doi.org/10.1007/s11042-021-10881-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-10881-5