Colorization of Grayscale Images using Deep Convolution Neural Networks
Keywords:
Colorization, Grayscale Images, Convolutional Neural Networks, CNN, Image Processing, Computer VisionAbstract
The work proposed in this paper is a high-performance colorization model that can be used in a wide range of applications such as colorization of old photos, restoration of damaged images, and even in the film and animation industry. It's not always the intention of colorization to restore an image to its exact ground truth color. Instead, even if the colorization differs slightly from the actual colors, the goal is to create believable shading that is aesthetically pleasing and helpful to the user. We have used a range of deep learning techniques along with Convolutional Neural Networks (CNNs) to achieve our goals. With the use of vast datasets of colored images, our software facilitates the development and instruction of deep CNNs, which are capable of extracting pertinent characteristics and recognizing relationships between them. The resulting knowledge is then applied to the task of predicting accurate colorizations of grayscale images.
Downloads
References
Deep Colorization and its Application to Re-Coloring" by Zhang, Richard and Isola, Phillip and Efros, Alexei A. (2020)
Real-Time Neural Style Transfer for Colorization" by Zhu, Jun-Yan and Zhang, Richard and Pathak, Deepak and Darrell, Trevor and Efros, Alexei A. and Wang, Oliver (2020)
Semantic Colorization with Weak Supervision" by Zhang, Richard and Zhu, Jun-Yan and Isola, Phillip and Geng, Xinyang and Lin, Angela and Yu, Tianhe and Efros, Alexei A. and Darrell, Trevor (2020).
Patch-Based Image Colorization with Generative Adversarial Networks" by Li, Jiayan and Wang, Xiaoping and Liu, Feng (2020).
Isola, Phillip, et al. "Image-to-image translation with conditional adversarial networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
Deshpande, Aditya, et al. "Learning diverse image colorization." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
Super-Resolving and Colorizing Grayscale Images using Generative Adversarial Networks" by Shrivastava, Avinash and Sukhwani, Siddharth and Agarwal, Ayush (2020).
Colorful Image Colorization" by Zhang, Richard and Isola, Phillip and Efros, Alexei A. (2020).
Li, R., Li, M., Zhang, B., Tao, D. (2022). A Lightweight Network for Fast Colorization of Grayscale Images. IEEE Transactions on Multimedia.
Image Colorization based on Generative Adversarial Networks" by Wang, Jiawei and Xu, Jingyuan and Liu, Jiaqi and Chang, Xiaojing (2020).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Abhishek Gudipalli, Canavoy Narahari Sujatha, Amutha Prabha N., Krishna Khanikhar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
