Ancient Book Image Restoration Using Generative Adversarial Networks
DOI:
https://doi.org/10.54097/70qk0p81Keywords:
Restoration of ancient books, Deep learning, Convolutional neural network, Adversarial generating network, Line guide.Abstract
As an important carrier of historical and cultural inheritance, the restoration of ancient books is of great significance to the protection of cultural relics and cultural inheritance. However, the traditional repair methods have some problems, such as low efficiency and insufficient precision. In this paper, a deep learning-based restoration method for ancient books is proposed, which is divided into two steps: structure reconstruction and color correction. The structure reconstruction network (SRN) uses line drawing information to ensure the authenticity and structural stability of large-scale content, and the color correction network (CCN) makes local color adjustments to missing pixels, reducing color bias and edge hopping problems. The experimental results show that this method effectively improves the restoration efficiency and image quality, and provides a new technical support for the protection and inheritance of ancient books.
Downloads
References
[1] Fangfang. Research on power load forecasting based on Improved BP neural network [D]. Harbin Institute of Technology, 2011.
[2] Amjady N. Short-term hourly load forecasting using time series modeling with peak load estimation capability [J]. IEEE Transactions on Power Systems, 2001, 16(4): 798-805.
[3] Ma Kunlong. Short term distributed load forecasting method based on big data [D]. Changsha: Hunan University, 2014.
[4] SHI Biao, LI Yu Xia, YU Xhua, YAN Wang. Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model [J]. Systems Engineering-Theory and Practice, 2010, 30(1): 158-160.
[5] Xu C ,Cui Y ,Zhang Y , et al.Image enhancement algorithm based on generative adversarial network in combination of improved game adversarial loss mechanism[J].Multimedia Tools and Applications,2019,79(prepublish):1-16.
[6] Sreekumar K ,Vimina R E .Multi-Label Classification of Fundus Images with Optimized Vision Transformer Based Wasserstein Deep Convolutional Generative Adversarial Network[J].SN Computer Science,2024,5(7):842-842.
[7] Li J ,Pan S ,Zhang X , et al.Generative Adversarial Networks with Radiomics Supervision for Lung Lesion Generation.[J].IEEE transactions on bio-medical engineering,2024,PP
[8] Kala R ,Chandrasekaran R ,Ahilan A , et al.Brain Magnetic Resonance Image Inpainting via Deep Edge Region-based Generative Adversarial Network[J].Journal of Electrical Engineering & Technology,2024,(prepublish):1-12.
[9] Vashistha R ,Vegh V ,Moradi H , et al.Modular GAN: positron emission tomography image reconstruction using two generative adversarial networks[J].Frontiers in Radiology,2024,41466498-1466498.
[10] Anantharajan S ,Gunasekaran S ,Sujana J A J .Brain tumor classification for combining the advantages of multilayer dense net-based feature extraction and hyper-parameters tuned attentive dual residual generative adversarial network classifier using wild horse optimization.[J].NMR in biomedicine,2024,e5246.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
