Virtual Restoration of Ancient Mold-Damaged Painting Based on 3D Convolutional Neural Network for Hyperspectral Image
Abstract
:1. Introduction
2. Materials and Methods
2.1. Materials
2.2. Spectral Characteristics of Silk-Based Mold
2.3. Data Processing before Virtual Restoration
2.4. Reconstruction of Mold Region Using 3D CNN
2.5. Quantitative Analysis
3. Results
4. Discussion
4.1. Quantitative Analysis
4.2. Classification of Pigments
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Lu, Y.; Kong, M. A Discussion on the Conservation and Restoration Methods for Mold-Damaged Calligraphy and Paintings. In Identification and Appreciation to Cultural Relic; Anhui Publishing Group Co., Ltd.: Hefei, China, 2021; pp. 98–100. [Google Scholar]
- Hou, M.; Wang, Q.; Tan, L.; Wu, W.; Lv, S. Virtual restoration of mildew stains on calligraphy and paintings based on abundance inversion and spectral transformation. Sci. Conserv. Archaeol. 2023, 35, 8–18. [Google Scholar]
- Li, Q.; Chen, J.; Xiong, L.; Guo, X.; Zhang, B.; Zhang, K.; Geng, J.; Ben, S. Identification of the Contaminated Fungus in the Ancient Books “ZhongyongDaxue”and the Removal of Mildew from Paper Samples. J. Liaoning Univ. (Nat. Sci. Ed.) 2019, 46, 294–299. [Google Scholar]
- Zhang, Y.; Liu, Z.; Liu, G.; Li, B.; Pan, J.; Ma, Q. Isolation and identification of fungi from some cultural relics and packaging boxes in Tianjin Museum storerooms. Sci. Conserv. Archaeol. 2019, 31, 61–67. [Google Scholar]
- Liu, S. Preliminary study on the damage mechanism of ancient paintings. Sci. Conserv. Archaeol. 2003, 15, 39–42. [Google Scholar]
- Yang, J. Mold identification and remediation of cultural relics based on scanning electron microscopy. J. Chin. Electron Microsc. Soc. 2020, 39, 65–70. [Google Scholar]
- Zhang, N.; Chen, X. Study on the Effect of Cleaning Agent for Paper Cultural Relics Mildew Spot; China Cultural Heritage Scientific Research: Beijing, China, 2018; pp. 70–74. [Google Scholar]
- Zhen, C.; Zhao, D. Research Progress of Bio-diseases on Paper Relics. J. Beijing Inst. Graph. Commun. 2019, 27, 32–37. [Google Scholar]
- Li, M. Prevention and Control of Mold Damage to Paper-Based Cultural Artifacts; China Cultural Heritage Scientific Research: Beijing, China, 2011; pp. 34–37. [Google Scholar]
- Hou, M.; Zhou, P.; Lv, S.; Hu, Y.; Zhao, X.; Wu, W.; He, H.; Li, S.; Tan, L. Virtual restoration of stains on ancient paintings with maximum noise fraction transformation based on the hyperspectral imaging. J. Cult. Herit. 2018, 34, 136–144. [Google Scholar] [CrossRef]
- Ma, Y. Research on Digital Oil Painting Based on Digital Image Processing Technology. In Proceedings of the 2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS), Shenyang, China, 11–13 December 2020; pp. 344–347. [Google Scholar]
- Rakhimol, V.; Maheswari, P.U. Restoration of ancient temple murals using cGAN and PConv networks. Comput. Graph. 2022, 109, 100–110. [Google Scholar] [CrossRef]
- Zhou, P.; Hou, M.; Lv, S.; Zhao, X.; Wu, W. Virtual Restoration of Stained Chinese Paintings Using Patch-Based Color Constrained Poisson Editing with Selected Hyperspectral Feature Bands. Remote Sens. 2019, 11, 1384. [Google Scholar] [CrossRef]
- Mishra, R.; Mittal, N.; Khatri, S.K. Digital Image Restoration using Image Filtering Techniques. In Proceedings of the 2019 International Conference on Automation, Computational and Technology Management (ICACTM), London, UK, 24–26 April 2019; pp. 268–272. [Google Scholar]
- Guillemot, C.; Meur, O.L. Image Inpainting: Overview and Recent Advances. IEEE Signal Process. Mag. 2014, 31, 127–144. [Google Scholar] [CrossRef]
- Pushpalwar, R.T.; Bhandari, S.H. Image Inpainting Approaches—A Review. In Proceedings of the 2016 IEEE 6th International Conference on Advanced Computing (IACC), Bhimavaram, India, 27–28 February 2016; pp. 340–345. [Google Scholar]
- Elharrouss, O.; Almaadeed, N.; Al-Maadeed, S.; Akbari, Y. Image Inpainting: A Review. Neural Process. Lett. 2020, 51, 2007–2028. [Google Scholar] [CrossRef]
- Li, M.; Qi, Q. Review of digital image restoration techniques. Inf. Commun. 2016, 29, 130–131. [Google Scholar]
- Pérez, P.; Gangnet, M.; Blake, A. Poisson Image Editing. ACM Trans. Graph. 2003, 22, 313–318. [Google Scholar] [CrossRef]
- Di Martino, J.M.; Facciolo, G.; Meinhardt-Llopis, E. Poisson Image Editing. Image Process. Line 2016, 6, 300–325. [Google Scholar] [CrossRef]
- Bertalmio, M.; Sapiro, G.; Caselles, V.; Ballester, C. Image Inpainting. In Proceedings of the 27th annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA, 23–28 July 2000; pp. 417–424. [Google Scholar]
- Chan, T.F.; Shen, J. Nontexture inpainting by curvature-driven diffusions. J. Vis. Commun. Image Represent. 2001, 12, 436–449. [Google Scholar] [CrossRef]
- Deng, C.; Wang, S.; Cao, H. Fourier-Curvelet Transform Combined Image Restoration. Acta Opt. Sin. 2009, 29, 2134–2137. [Google Scholar] [CrossRef]
- Yaroslavsky, L. Compression, restoration, resampling, 'compressive sensing’: Fast transforms in digital imaging. J. Opt. 2015, 17, 073001. [Google Scholar] [CrossRef]
- Jiang, J.; Deng, Q.; Zhang, G. Regularization algorithm for blind image restoration based on wavelet transform. Opt. Precis. Eng. 2007, 15, 582–586. [Google Scholar]
- Starck, J.-L.; Fadili, J.; Murtagh, F. The undecimated wavelet decomposition and its reconstruction. EEE Trans. Image Process. 2007, 16, 297–309. [Google Scholar] [CrossRef]
- Hong, H.; Zhang, T. Fast restoration algorithm for turbulence-degraded images based on wavelet decomposition. J. Infrared Millim. Waves 2003, 22, 451–456. [Google Scholar]
- Su, Z.; Zhu, S.; Lv, X.; Wan, Y. Image restoration using structured sparse representation with a novel parametric data-adaptive transformation matrix. Signal Process. Image Commun. 2017, 52, 151–172. [Google Scholar] [CrossRef]
- Chen, Y.; Tao, M.; Ai, Y.; Chen, J. Algorithm for Dunhuang Mural Inpainting Based on Gabor Transform and Group Sparse Representation. Laser Optoelectron. Prog. 2020, 57, 221015. [Google Scholar] [CrossRef]
- Li, J.; Chen, X.; Zou, D.; Gao, B.; Teng, W. Conformal and Low-Rank Sparse Representation for Image Restoration. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; pp. 235–243. [Google Scholar]
- Hanif, M.; Tonazzini, A.; Savino, P.; Salerno, E. Non-Local Sparse Image Inpainting for Document Bleed-Through Removal. J. Imaging 2018, 4, 68. [Google Scholar] [CrossRef]
- Barnes, C.; Shechtman, E.; Finkelstein, A.; Goldman, D.B. PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Trans. Graph. (TOG) 2009, 28, 24. [Google Scholar] [CrossRef]
- Newson, A.; Almansa, A.; Gousseau, Y.; Pérez, P. Non-Local Patch-Based Image Inpainting. Image Process. Line 2017, 7, 373–385. [Google Scholar] [CrossRef]
- Criminisi, A.; Pérez, P.; Toyama, K. Object removal by exemplar-based inpainting. In Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA, 18–20 June 2003; pp. 721–728. [Google Scholar]
- Wang, H.; Jiang, L.; Liang, R.; Li, X.-X. Exemplar-based image inpainting using structure consistent patch matching. Neurocomputing 2017, 269, 90–96. [Google Scholar] [CrossRef]
- Zhang, L.; Wang, S.; Zhang, Y.; Yuan, D.; Song, R.; Qi, W.; Qu, L.; Lu, Z.; Tong, Q. Progress of hyperspectral remote sensing applications on cultural relics protection. Acta Geod. Cartogr. Sin. 2023, 52, 1126–1138. [Google Scholar]
- Zhou, P.; Miaole, H.; Zhao, X.; Lv, S.; Hu, Y.; Zhang, X.; Zhao, H. Virtual Restoration of Ancient Painting Stains Based on Classified Linear Regression of Hyper-spectral Image. Geomat. World 2017, 24, 113–118. [Google Scholar]
- Yang, W.; Tang, X.; Zhang, P.; Hu, B.; JIn, Z. Research on a method for virtual restoration of the colors of tomb mural pigments based on spectral fusion analysis. Sci. Conserv. Archaeol. 2023, 35, 11–23. [Google Scholar]
- Li, G.; Chen, Y.; Duan, P.; Qu, L.; Sun, X.; Zhang, H.; Lei, Y. Study on the application of an automatic hyperspectral scanning system to investigate Chinese paintings. Chin. Mus. 2021, S2, 180–185. [Google Scholar]
- Yan, L.; Gao, Y.; Jia, D. Isolation and identification of contaminated mold on ancient painting and calligraphy relics. China Cult. Herit. Sci. Res. 2011, 78–82. [Google Scholar]
- Cappitelli, F.; Principi, P.; Pedrazzani, R.; Toniolo, L.; Sorlini, C. Bacterial and fungal deterioration of the Milan Cathedral marble treated with protective synthetic resins. Sci. Total Environ. 2007, 385, 172–181. [Google Scholar] [CrossRef]
- Malešič, J.; Kolar, J.; Strlič, M.; Kočar, D.; Fromageot, D.; Lemaire, J.; Haillant, O. Photo-induced degradation of cellulose. Polym. Degrad. Stab. 2005, 89, 64–69. [Google Scholar] [CrossRef]
- Cen, Y.; Zhang, L.; Sun, X.; Zhang, L.; Lin, H.; Zhao, H.; Wang, X. Spectral Analysis of Main Mineral Pigments in Thangka. Spectrosc. Spectr. Anal. 2019, 39, 1136–1142. [Google Scholar]
- Yu, Q. Research on Optical Fiber Sensor for Online Detection of Mold and Disease Process Parameters on Paper Cultural Relics; Chongqing University of Technology: Chongqing, China, 2023. [Google Scholar]
- Qu, L.-L.; Jia, Q.; Liu, C.; Wang, W.; Duan, L.; Yang, G.; Han, C.-Q.; Li, H. Thin layer chromatography combined with surface-enhanced raman spectroscopy for rapid sensing aflatoxins. J. Chromatogr. A 2018, 1579, 115–120. [Google Scholar] [CrossRef]
- Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Qi, W.; Zhang, X.; Wang, N.; Zhang, M.; Cen, Y. A Spectral-Spatial Cascaded 3D Convolutional Neural Network with a Convolutional Long Short-Term Memory Network for Hyperspectral Image Classification. Remote Sens. 2019, 11, 2363. [Google Scholar] [CrossRef]
- Ioffe, S.; Szegedy, C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Proceedings of the 32nd International Conference on International Conference on Machine Learning, Lille, France, 7–9 July 2015; pp. 448–456. [Google Scholar]
- Bengio, Y.; Simard, P.; Frasconi, P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 1994, 5, 157–166. [Google Scholar] [CrossRef]
- Telea, A. An Image Inpainting Technique Based on the Fast Marching Method. J. Graph. Tools 2004, 9, 25–36. [Google Scholar] [CrossRef]
Parameters | VNIR | SWIR |
---|---|---|
Spectral range/nm | 400–1000 | 950–2500 |
Spectral sampling/nm | 1.6 | 9.6 |
Sensor type | sCMOS | Stirling cooled MCT |
Digitalizing bit | 16 bit | 16 bit |
Slit width/µm | 20 | 25 |
Light source | halogen lamp | halogen lamp |
RMSE | MAPE | MAE | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
R | G | B | R | G | B | R | G | B | ||
White material on the face | Original | 0.0648 | 0.0667 | 0.1238 | 8.4878 | 13.5048 | 29.5463 | 0.0476 | 0.0541 | 0.1183 |
Inverse MNF transformation | 0.0600 | 0.0616 | 0.1182 | 7.6019 | 12.2222 | 28.1356 | 0.0427 | 0.0489 | 0.1126 | |
Inpainting | 0.0949 | 0.0811 | 0.1348 | 11.4468 | 14.4198 | 31.4747 | 0.0642 | 0.0577 | 0.1260 | |
Criminisi | 0.0882 | 0.0731 | 0.1305 | 10.1655 | 11.9957 | 29.2393 | 0.0570 | 0.0480 | 0.1170 | |
3D CNN | 0.0503 | 0.0510 | 0.0989 | 6.3177 | 9.8145 | 22.4118 | 0.0355 | 0.0393 | 0.0897 | |
White material on hand | Original | 0.0799 | 0.0868 | 0.0668 | 9.8863 | 14.7794 | 14.0087 | 0.0592 | 0.0664 | 0.0503 |
Inverse MNF transformation | 0.0722 | 0.0790 | 0.0594 | 8.8873 | 13.4263 | 12.3301 | 0.0532 | 0.0604 | 0.0442 | |
Inpainting | 0.0756 | 0.0631 | 0.0559 | 7.6091 | 9.2662 | 10.4840 | 0.0456 | 0.0417 | 0.0376 | |
Criminisi | 0.1130 | 0.0908 | 0.0792 | 9.9254 | 11.8401 | 13.8018 | 0.0594 | 0.0532 | 0.0495 | |
3D CNN | 0.0576 | 0.0477 | 0.0425 | 6.9609 | 7.9137 | 8.9051 | 0.0417 | 0.0356 | 0.0319 |
RMSE | MAPE | MAE | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
R | G | B | R | G | B | R | G | B | ||
Light red material | Original | 0.0626 | 0.0517 | 0.0316 | 8.6691 | 13.3147 | 11.8176 | 0.0493 | 0.0423 | 0.0260 |
Inverse MNF transformation | 0.0433 | 0.0328 | 0.0254 | 6.0930 | 8.5844 | 9.3905 | 0.0347 | 0.0272 | 0.0207 | |
Inpainting | 0.0361 | 0.0286 | 0.0235 | 4.8210 | 6.9725 | 8.3940 | 0.0274 | 0.0221 | 0.0185 | |
Criminisi | 0.0343 | 0.0288 | 0.0232 | 4.6273 | 7.3410 | 8.5941 | 0.0263 | 0.0233 | 0.0189 | |
3D CNN | 0.0383 | 0.0337 | 0.0276 | 5.1616 | 8.2030 | 10.0719 | 0.0294 | 0.0260 | 0.0222 | |
Crimson material | Original | 0.0845 | 0.0565 | 0.0302 | 12.6938 | 17.7171 | 13.3757 | 0.0650 | 0.0459 | 0.0239 |
Inverse MNF transformation | 0.0548 | 0.0415 | 0.0342 | 8.3783 | 12.9686 | 15.1888 | 0.0429 | 0.0336 | 0.0271 | |
Inpainting | 0.0590 | 0.0385 | 0.0239 | 8.2551 | 11.6485 | 10.7408 | 0.0423 | 0.0301 | 0.0192 | |
Criminisi | 0.0585 | 0.0511 | 0.0359 | 9.0721 | 16.4108 | 16.3552 | 0.0465 | 0.0425 | 0.0292 | |
3D CNN | 0.0547 | 0.0374 | 0.0242 | 8.1121 | 11.1807 | 10.0496 | 0.0416 | 0.0289 | 0.0179 |
RMSE | MAPE | MAE | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
R | G | B | R | G | B | R | G | B | ||
Brown background | Original | 0.0983 | 0.1111 | 0.0949 | 17.5595 | 26.6170 | 27.2211 | 0.0766 | 0.0884 | 0.0738 |
Inverse MNF transformation | 0.0839 | 0.0766 | 0.0766 | 14.9242 | 18.2449 | 22.2645 | 0.0651 | 0.0606 | 0.0603 | |
Inpainting | 0.1195 | 0.1052 | 0.0927 | 19.3230 | 22.8916 | 25.3922 | 0.0843 | 0.0760 | 0.0688 | |
Criminisi | 0.1178 | 0.1032 | 0.0957 | 19.9626 | 23.4313 | 27.1039 | 0.0871 | 0.0778 | 0.0735 | |
3D CNN | 0.0776 | 0.0739 | 0.0832 | 13.1059 | 16.2916 | 23.2589 | 0.0572 | 0.0541 | 0.0630 |
Class | Original | Inverse MNF Transformation | Inpainting | Criminisi | 3D CNN | |||||
---|---|---|---|---|---|---|---|---|---|---|
Prod. Accuracy (%) | User. Accuracy (%) | Prod. Accuracy (%) | User. Accuracy (%) | Prod. Accuracy (%) | User. Accuracy (%) | Prod. Accuracy (%) | User. Accuracy (%) | Prod. Accuracy (%) | User. Accuracy (%) | |
Region1 Lady’s picture | ||||||||||
Red | 98.33 | 100 | 98.33 | 100 | 98.33 | 100 | 98.33 | 100 | 96.67 | 100 |
Black | 93.33 | 93.33 | 95 | 93.44 | 91.67 | 91.67 | 91.67 | 91.67 | 98.33 | 96.72 |
Light Red | 59.26 | 96.97 | 51.67 | 96.88 | 55 | 100 | 55 | 100 | 63.33 | 100 |
Blue | 98 | 92.45 | 98 | 98 | 98 | 94.23 | 98 | 94.23 | 100 | 90.91 |
White | 84.13 | 70.67 | 85.29 | 67.44 | 86.76 | 70.24 | 82.35 | 69.14 | 88.24 | 75 |
Cyan | 90 | 88.24 | 96 | 90.57 | 92 | 86.79 | 92 | 86.79 | 88 | 86.27 |
Yellow | 92 | 85.19 | 92 | 83.64 | 92 | 85.19 | 92 | 85.19 | 92 | 88.46 |
Brown | 94 | 90.38 | 92 | 88.46 | 94 | 88.68 | 94 | 83.93 | 92 | 86.79 |
Overall Accuracy | 88.56% | 87.95% | 87.95% | 87.28% | 89.51% | |||||
Kappa Coefficient | 0.87 | 0.86 | 0.86 | 0.85 | 0.88 | |||||
Region2 Clothes’ picture | ||||||||||
Red | 100 | 90.48 | 100 | 82.19 | 100 | 77.92 | 100 | 77.92 | 100 | 85.71 |
Deep Red | 100 | 100 | 96.67 | 100 | 96.67 | 100 | 96.67 | 100 | 96.67 | 100 |
White | 92.5 | 97.37 | 97.5 | 92.86 | 92.5 | 100 | 92.5 | 100 | 92.5 | 100 |
Black | 87.5 | 94.59 | 92.5 | 97.37 | 80 | 96.97 | 80 | 96.97 | 90 | 97.3 |
Yellow | 90 | 100 | 90 | 100 | 87.5 | 100 | 87.5 | 100 | 90 | 100 |
Offwhite | 95 | 95 | 88.33 | 98.15 | 95 | 96.61 | 95 | 96.61 | 93.33 | 94.92 |
Cyan | 90 | 94.74 | 90 | 100 | 90 | 85.71 | 90 | 85.71 | 90 | 97.3 |
Brown | 90 | 79.41 | 93.33 | 83.58 | 91.67 | 83.33 | 91.67 | 83.33 | 91.67 | 79.71 |
Black red | 98.08 | 91.07 | 90 | 88.52 | 90 | 88.52 | 91.67 | 88.71 | 98.33 | 90.77 |
Dark teal | 93.33 | 93.33 | 93.33 | 93.33 | 93.33 | 93.33 | 93.33 | 93.33 | 93.33 | 93.33 |
Gray | 76.67 | 86.79 | 78.33 | 85.45 | 76.67 | 88.46 | 76.67 | 90.2 | 76.67 | 88.46 |
Overall Accuracy | 92.25% | 91.72% | 90.69% | 90.86% | 92.24% | |||||
Kappa Coefficient | 0.91 | 0.91 | 0.90 | 0.90 | 0.91 | |||||
Region3 Branch’s picture | ||||||||||
Red | 90.16 | 98.21 | 95.08 | 89.23 | 96.72 | 83.1 | 98.36 | 81.08 | 91.8 | 98.25 |
Gray | 98.33 | 93.65 | 98.33 | 96.72 | 98.33 | 89.39 | 98.33 | 95.16 | 98.33 | 93.65 |
White | 95 | 100 | 93.33 | 100 | 95 | 100 | 95 | 100 | 93.33 | 100 |
Black | 91.67 | 94.83 | 93.33 | 90.32 | 88.33 | 100 | 93.33 | 96.55 | 91.67 | 100 |
Brown | 88.33 | 77.94 | 96.67 | 87.88 | 95 | 79.17 | 88.33 | 81.54 | 95 | 89.06 |
Background | 94.12 | 87.27 | 100 | 92.31 | 93.33 | 91.8 | 95 | 91.94 | 96.67 | 86.57 |
Light gray | 60 | 62.07 | 76.67 | 82.14 | 43.33 | 72.22 | 46.67 | 60.87 | 80 | 72.73 |
Cyan | 96 | 100 | 88 | 100 | 96 | 100 | 96 | 100 | 96 | 100 |
Yellow | 93.33 | 100 | 80 | 100 | 83.33 | 100 | 73.33 | 100 | 93.33 | 100 |
Overall Accuracy | 91.13% | 93.00% | 90.66% | 90.45% | 93.63% | |||||
Kappa Coefficient | 0.90 | 0.92 | 0.89 | 0.89 | 0.93 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, S.; Cen, Y.; Qu, L.; Li, G.; Chen, Y.; Zhang, L. Virtual Restoration of Ancient Mold-Damaged Painting Based on 3D Convolutional Neural Network for Hyperspectral Image. Remote Sens. 2024, 16, 2882. https://doi.org/10.3390/rs16162882
Wang S, Cen Y, Qu L, Li G, Chen Y, Zhang L. Virtual Restoration of Ancient Mold-Damaged Painting Based on 3D Convolutional Neural Network for Hyperspectral Image. Remote Sensing. 2024; 16(16):2882. https://doi.org/10.3390/rs16162882
Chicago/Turabian StyleWang, Sa, Yi Cen, Liang Qu, Guanghua Li, Yao Chen, and Lifu Zhang. 2024. "Virtual Restoration of Ancient Mold-Damaged Painting Based on 3D Convolutional Neural Network for Hyperspectral Image" Remote Sensing 16, no. 16: 2882. https://doi.org/10.3390/rs16162882