The week's pick
Reseach Article
A Comprehensive Review of Illuminating and restoring Old images using Deep Learning Techniques
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 68 |
| Year of Publication: 2025 |
| Authors: Siva Kavya Karyampudi, Kommi Varshith Chowdary, Kalpana Ettikyala |
10.5120/ijca2025924496
|
Siva Kavya Karyampudi, Kommi Varshith Chowdary, Kalpana Ettikyala . A Comprehensive Review of Illuminating and restoring Old images using Deep Learning Techniques. International Journal of Computer Applications. 186, 68 ( Feb 2025), 15-19. DOI=10.5120/ijca2025924496
Abstract
The preservation and restoration of old, damaged, and black-and-white photographs pose a significant challenge due to factors such as color fading, noise, cracks, and other degradations over time. Many historical, cultural, and personal images have deteriorated, leading to a loss of visual clarity, color information, and overall image quality. Traditional image restoration methods are limited in their ability to accurately reconstruct fine details and add vibrant, realistic colors to these images. With the advancements in deep learning techniques, there is an opportunity to develop an automated system for both image colorization and image restoration. By using Generative Adversarial Networks (GANs) for colorization and Convolutional Neural Networks (CNNs) for restoration, a combined model can be proposed that achieves high-quality, visually appealing results.
References
- H. Shafiq and B. Lee, "Image Colorization Using Color-Features and Adversarial Learning," in IEEE Access, vol. 11, pp. 132811-132821, 2023, doi: 10.1109/ACCESS.2023.3335225.
- Y. Cui, W. Ren, X. Cao and A. Knoll, "Revitalizing Convolutional Network for Image Restoration," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 9423-9438, 2024, doi: 10.1109/TPAMI.2024.3419007.
- S. W. Zamir et al., "Learning Enriched Features for Fast Image Restoration and Enhancement" in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 45, no. 02, pp. 1934-1948, Feb. 2023, doi: 10.1109/TPAMI.2022.3167175.
- K. Du, C. Liu, L. Cao, Y. Guo, F. Zhang and T. Wang, "Double-Channel Guided Generative Adversarial Network for Image Colorization," in IEEE Access, vol. 9, pp. 21604-21617, 2021, doi: 10.1109/ACCESS.2021.3055575.
- Shafiq, Hamza, and Bumshik Lee. 2024. "Transforming Color: A Novel Image Colorization Method" Electronics 13, no. 13: 2511. https://doi.org/10.3390/electronics13132511.
- F. Ozcelik, U. Alganci, E. Sertel and G. Unal, "Rethinking CNN-Based Pansharpening: Guided Colorization of Panchromatic Images via GANs," in IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 4, pp. 3486-3501, April 2021, doi: 10.1109/TGRS.2020.3010441.
- Treneska, Sandra, Eftim Zdravevski, Ivan Miguel Pires, Petre Lameski, and Sonja Gievska. 2022. "GAN-Based Image Colorization for Self-Supervised Visual Feature Learning" Sensors 22, no. 4: 1599. https://doi.org/10.3390/s22041599.
- Cao M, Feng H, Xiao H. An Improved GAN-Based Image Restoration Method for Imaging Logging Images. Applied Sciences. 2023; 13(16):9249. https://doi.org/10.3390/app13169249.
- Joshi MR, Nkenyereye L, Joshi GP, Islam SMR, Abdullah-Al-Wadud M, Shrestha S. Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks. Mathematics. 2020; 8(12):2258. https://doi.org/10.3390/math8122258.
- F. Muscat and T. Gatt, "Black and White Image Colourisation Using Deep Learning Techniques," 2023 International Symposium on Image and Signal Processing and Analysis (ISPA), Rome, Italy, 2023, pp. 1-6, doi: 10.1109/ISPA58351.2023.10278865.
Index Terms
Keywords