The Application of U-Net and Image Colorfulness Frame for Image Colorization Issue
The Application of U-Net and Image Colorfulness Frame for Image Colorization Issue |
||
![]() |
![]() |
|
© 2024 by IJETT Journal | ||
Volume-72 Issue-7 |
||
Year of Publication : 2024 | ||
Author : Hani Q. R. Al‐Zoubi |
||
DOI : 10.14445/22315381/IJETT-V72I7P103 |
How to Cite?
Hani Q. R. Al‐Zoubi, "The Application of U-Net and Image Colorfulness Frame for Image Colorization Issue," International Journal of Engineering Trends and Technology, vol. 72, no. 7, pp. 24-36, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I7P103
Abstract
This paper proposes a novel approach to the image colorization problem by fusing U-Net architecture with Image Colorfulness Frame (ICF). The proposed method aims to overcome the limitations of existing colorization methods, which often produce pixelated and subpar photos. Color maps are produced using the U-Net architecture using the grayscale input photographs. The color maps' vibrancy is then evaluated using the ICF. The ICF helps to make colorization results more accurate and aesthetically pleasant. Experimental results show that the proposed method outperforms the state-of-the-art methods in terms of colorization accuracy and visual quality. The suggested method has many applications, including colorizing films and photos, restoring black and white images, and colorizing historical images.
Keywords
U-Net Grayscale photos, Color maps, Image colorization, Picture colorfulness assessment, Realistic colorization, Historical image colorization and black and white image repair.
References
[1] Youssef Mourchid, Marc Donias, and Yannick Berthoumieu, “Dual Color-Image Discriminators Adversarial Networks for Generating Artificial-SAR Colorized Images from SENTINEL-1 Images,” Machine Learning for Earth Observation Workshop, 2020.
[Google Scholar] [Publisher Link]
[2] Kamyar Nazeri, Eric Ng, and Mehran Ebrahimi, “Image Colorization Using Generative Adversarial Networks,” Articulated Motion and Deformable Objects: 10th International Conference, Palma de Mallorca, Spain, pp. 85-94, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Leila Kiani, Masoud Saeed, and Hossein Nezamabadi-Pour, “Image Colorization Using Generative Adversarial Networks and Transfer Learning,” 2020 International Conference on Machine Vision and Image Processing, Iran, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mohammad Mahdi Johari, and Hamid Behroozi, “Gray-Scale Image Colorization using Cycle-Consistent Generative Adversarial Networks with Residual Structure Enhancer,” ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain, pp. 2223-2227, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Sindhuja Kotala et al., “Automatic Colorization of Black and White Images using Deep Learning,” International Journal of Computer Science and Network, vol. 8, no. 2, pp. 125-131, 2019.
[Google Scholar] [Publisher Link]
[6] Sudesh Pahal, and Preeti Sehrawat, “Image Colorization with Deep Convolutional Neural Networks,” Advances in Communication and Computational Technology, pp. 45-56, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Elisa Mariarosaria Farella, Salim Malek, and Fabio Remondino, “Colorizing the Past: Deep Learning for the Automatic Colorization of Historical Aerial Images,” Journal of Imaging, vol. 8, no. 10, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jiayi Fan, Wentao Xie, and Tiantian Ge, “Automatic Gray Image Coloring Method Based on Convolutional Network,” Computational Intelligence and Neuroscience, pp. 1-9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Md. Istiak Hossain Shihab et al., “VISTA: Vision Transformer Enhanced by U-Net and Image Colorfulness Frame Filtration for Automatic Retail Checkout,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3183-3191, 2022.
[Google Scholar] [Publisher Link]
[10] Mohammad Amir Qureshi et al., “Automatic Image Colorization with Convolutional Neural Networks,” 2021 Asian Conference on Innovation in Technology, Pune, India, pp. 1-4, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] S.J. Sugumar, “Colorization of Digital Images: An Automatic and Efficient Approach through Deep Learning,” Journal of Innovative Image Processing, vol. 4, no. 3, pp. 183-194, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Muhammad Hisyam Zayd, Novanto Yudistira, and Randy Cahya Wihandika, “Image Colorization Using U-Net with Skip Connections and Fusion Layer on Landscape Images,” arXiv, pp. 1-7, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Qifeng Chen, and Vladlen Koltun, “Photographic Image Synthesis with Cascaded Refinement Networks,” Proceedings of the IEEE International Conference on Computer Vision, pp. 1511-1520, 2017.
[Google Scholar] [Publisher Link]
[14] Laia Tarrés Benet, “GAN-Based Image Colourisation with Feature Reconstruction Loss,” Master's Thesis, Universitat Politècnica de Catalunya, 2021.
[Google Scholar] [Publisher Link]
[15] Richard Zhang, Phillip Isola, and Alexei A. Efros, “Colorful Image Colorization,” Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, pp. 649-666, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Satoshi Iizuka, Edgar Simo-Serra, and Hiroshi 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, 2016.
[CrossRef] [Google Scholar] [Publisher Link]