A Study on Image Quality Improvement for 3D Pagoda Restoration
Keywords:
SRGAN algorithm, Pagoda image resolution, image histogram, super resolution algorithmAbstract
The SRGAN algorithm based on the Generative Adversarial Networks (GANS) algorithm is used for image generation, image restoration, and resolution improvement. In this study, we proposed a method to improve the quality of pagoda images to create a 3D model by combining several 2D pagoda images. In the study, the SRGAN artificial intelligence algorithm was used to minimize the noise generated when converting low-quality images into 3D models. Low resolution, high resolution and super resolution results were obtained with the SRGAN algorithm by selecting the low quality of the Pagoda image dataset. In addition, the degree of resolution improvement was confirmed by collecting quantified R, G, and B information through histogram analysis. The research results will be used as a dataset for converting 2D images into 3D models.
Downloads
References
Johnson, Justin & Alahi, Alexandre & Fei-Fei, Li. (2016). Perceptual Losses for Real-Time Style Transfer and Super-Resolution. 9906. 694-711. 10.1007/978-3-319-46475-6_43. DOI: https://doi.org/ 10.48550/ arXiv.1603.08155
J. Li, L. Wu, S. Wang, W. Wu, F. Song and G. Zheng(2019), "Super Resolution Image Reconstruction of Textile Based on SRGAN," 2019 IEEE International Conference on Smart Internet of Things (SmartIoT), 2019, pp. 436-439, doi: 10.1109/SmartIoT.2019.00078.
S. H. Salem Hussin and R. Yildirim (2021), "StyleGAN-LSRO Method for Person Re-Identification," in IEEE Access, vol. 9, pp. 13857-13869, doi: 10.1109/ACCESS.2021.3051723.
J. Osorio Ríos, A. Armejach, G. Khattak, E. Petit, S. Vallecorsa and M. Casas(2020), "Evaluating Mixed-Precision Arithmetic for 3D Generative Adversarial Networks to Simulate High Energy Physics Detectors," 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 49-56, doi: 10.1109/ICMLA51294.2020.00017.
Y. Lecun, L. Bottou, Y. Bengio and P. Haffner (1998), "Gradient-based learning applied to document recognition", Proceedings of the IEEE, pp. 2278-2324.
D. Salamani et al., (2018), "Deep Generative Models for Fast Shower Simulation in ATLAS", Proceedings 14th International Conference on e-Science: Amsterdam Netherlands October 29-November 1 2018, pp. 348.
X. Jiang, Y. Xu, P. Wei and Z. Zhou (2020), "CT Image Super Resolution Based on Improved SRGAN," 2020 5th International Conference on Computer and Communication Systems (ICCCS), 2020, pp. 363-367, doi: 10.1109/ICCCS49078.2020.9118497.
N. Xiang, B. Tang and L. Wang (2022), "Image Super-Resolution Method Based on Improved Generative Adversarial Network," 2022 IEEE 5th International Conference on Electronics Technology (ICET), 2022, pp. 1207-1212, doi: 10.1109/ICET55676.2022.9824258.
X. Hou, T. Liu, S. Wang and L. Zhang (2021), "Image Quality Improve by Super Resolution Generative Adversarial Networks," 2021 2nd International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI), 2021, pp. 117-121, doi: 10.1109/ICHCI54629.2021.00031.
N. A. Gowtham, S. Deepakq and D. Patra(2020), "Super-Resolution Generative Adversarial Network with Modified Architecture for Single Image Super-Resolution," 2020 4th International Conference on Computer, Communication and Signal Processing (ICCCSP), 2 pp. 1-6, doi: 10.1109/ICCCSP49186.2020.9315285.
D. Lee, S. Lee, H. Lee, K. Lee and H. -J. Lee(2019), "Resolution-Preserving Generative Adversarial Networks for Image Enhancement," in IEEE Access, vol. 7, pp. 110344-110357, doi: 10.1109/ ACCESS.2019.2934320.
S. N. Ferdous, A. Dabouei, J. Dawson and N. M. Nasrabadi (2021), "Super-resolution Guided Pore Detection for Fingerprint Recognition," 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 8085-8092, doi: 10.1109/ICPR48806.2021.9413043.
W. Ma, Z. Pan, J. Guo and B. Lei (2018), "Super-Resolution of Remote Sensing Images Based on Transferred Generative Adversarial Network," IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018, pp. 1148-1151, doi: 10.1109/IGARSS.2018.8517442.
H. N. Pathak, X. Li, S. Minaee and B. Cowan (2018), "Efficient Super Resolution for Large-Scale Images Using Attentional GAN," 2018 IEEE International Conference on Big Data (Big Data), pp. 1777-1786, doi: 10.1109/BigData.2018.8622477.
Z. San-You, C. De-Qiang, J. Dai-Hong, K. Qi-Qi and M. Lu(2020), "Adaptive Diagonal Total-Variation Generative Adversarial Network for Super-Resolution Imaging," in IEEE Access, vol. 8, pp. 57517-57526, 2020, doi: 10.1109/ACCESS.2020.2981726.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Byong-Kwon Lee
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.
