Abstract
Converting a grayscale image to a visually plausible and perceptually meaningful color image is an exciting research topic in computer vision and graphics. However, predicting the chrominance channels from a grayscale image is an ill-posed problem, especially when the objective is to produce the same color as in the ground truth image, like for the application of compression using colorization or video/image restoration. Compression using colorization efficiently reduces the storage space and transmission bandwidth by two-thirds and maintains the image’s visual quality. However, colorizing decompressed gray images exactly as ground truth with maximum accuracy is a challenging task. In this paper, learning-based CNN network ColCompNeT has been proposed in which concept of parallel training of colorization and compression network is utilized. With the proposed algorithm, a maximum bit saving of 36.45% is achieved with the improved objective and subjective performance when compared with the state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baig MH, Torresani L (2017) Multiple hypothesis colorization and its application to image compression. Comput Vis Image Understanding 164:111–123
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 Graphics (TOG) 35(4):110
Zhang R, Isola P, Efros AA (2016) Colorful image colorization. In: European conference on computer vision. Springer, Heidelberg, pp 649–666
Singh SK, Kumar S (2011) Singular value decomposition based sub-band decomposition and multi-resolution (SVD-SBD-MRR) representation of digital colour images. Pertanika J Sci Technol (JST) 19(2):229–235
Singh SK, Kumar S (2009) Improved image compression based on feed-forward adaptive downsampling algorithm. Int J Image Graphics 9(04):575–589
Singh SK, Kumar S (2011) Novel adaptive color space transform and application to image compression. Signal Process: Image Commun 26(10):662–672
Singh SK, Kumar S (2010) Mathematical transforms and image compression: a review. Maejo Int J Sci Technol 4(2):235–249
Mishra D, Singh SK, Singh RK (2021) Wavelet-based deep auto encoder-decoder (WDAED)-based image compression. IEEE Trans Circuits Syst Video Technol 31(4):1452–1462. https://doi.org/10.1109/TCSVT.2020.3010627
Mishra D, Singh SK, Singh RK (2020) Lossy medical image compression using residual learning-based dual autoencoder model. In: 2020 IEEE 7th Uttar Pradesh section international conference on electrical, electronics and computer engineering (UPCON), pp 1–5. https://doi.org/10.1109/UPCON50219.2020.9376417
Mishra D, Singh SK, Singh RK, Kedia D (2021) Multi-scale network (MsSG-CNN) for joint image and saliency map learning-based compression. Neurocomputing 460:95–105. https://doi.org/10.1016/j.neucom.2021.07.012. https://www.sciencedirect.com/science/article/pii/S0925231221010468
Mishra D, Singh SK, Singh RK (2021b) Deep architectures for image compression: a critical review. Signal Process 108346. https://doi.org/10.1016/j.sigpro.2021.108346, https://www.sciencedirect.com/science/article/pii/S0165168421003832
Cui MY, Zhu Z, Yang Y, Lu SP (2022) Towards natural object-based image recoloring. Comput Vis Media 8(2):317–328
Neogi D, Das N, Deb S (2022) A deep neural approach toward staining and tinting of monochrome images. In: Advanced computing and intelligent technologies. Springer, Heidelberg, pp 25–36
Cheng L, Vishwanathan S (2007) Learning to compress images and videos. In: Proceedings of the 24th international conference on Machine learning. ACM, pp 161–168
He X, Ji M, Bao H (2009) A unified active and semi-supervised learning framework for image compression. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 65–72
Ono S, Miyata T, Sakai Y (2010) Colorization-based coding by focusing on characteristics of colorization bases. In: 28th picture coding symposium. IEEE, pp 230–233
Lee S, Park SW, Oh P, Kang MG (2013) Colorization-based compression using optimization. IEEE Trans Image Process 22(7):2627–2636
Wallace GK (1992) The jpeg still picture compression standard. IEEE Trans Consumer Electronics 38(1):xviii–xxxiv
Christopoulos C, Skodras A, Ebrahimi T (2000) The jpeg2000 still image coding system: an overview. IEEE Trans Consumer Electronics 46(4):1103–1127
Deshmukh S, Tiwari V (2015) Colorization based compression using fuzzy c-means and smooth l0 minimization. In: 2015 international conference on computer, communication and control (IC4). IEEE, pp 1–4
Su JW, Chu HK, Huang JB (2020) Instance-aware image colorization. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7968–7977
Sheikh HR, Wang Z, Cormack L, Bovik AC (2005) LIVE image quality assessment database release, 2
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: International conference on curves and surfaces. Springer, Heidelberg, pp 711–730
MacKnight CB (1995) Kodak Photo CD Eastman Kodak Company Kodak Information Center Department E 343 State Street Rochester, NY 14650–0811. J Comput Higher Educ 7(1):129–131. https://doi.org/10.1007/BF02946148
Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Climate Res 30(1):79–82
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. CoRR abs/1412.6980
Salomon D (2004) Data compression: the complete reference. Springer Science & Business Media
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mishra, D., Singh, S.K. (2023). ColCompNeT: Deep Learning-Based Colorization-Based Coding Network. In: Sisodia, D.S., Garg, L., Pachori, R.B., Tanveer, M. (eds) Machine Intelligence Techniques for Data Analysis and Signal Processing. Lecture Notes in Electrical Engineering, vol 997. Springer, Singapore. https://doi.org/10.1007/978-981-99-0085-5_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-0085-5_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0084-8
Online ISBN: 978-981-99-0085-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)