Revealing latent linear structures in murals via joint analysis of hyperspectral and visible images
Source abstract
Abstract
As vital components of cultural heritage, murals preserve rich linear structural information that is often obscured by aging and surface contamination. Existing studies have demonstrated the value of hyperspectral imaging for mural analysis, but robust cross-modal registration with visible images and reliable extraction of subtle latent line features remain challenging. This paper proposes a joint hyperspectral–visible analysis method for revealing candidate latent linear structures. The method integrates hyperspectral enhancement, PCA-based representative image generation, edge-domain registration, and edge-corner kernel density differencing. Experiments on the Baisha murals achieved sub-pixel registration accuracy (RMSE < 1 pixel) and revealed latent linear structures that were indistinct in visible images. These results demonstrate the effectiveness of the proposed method for hyperspectral–visible image registration and its potential for assisting mural analysis and conservation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Image Processing and 3D Reconstruction · 3D Surveying and Cultural Heritage · 3D Shape Modeling and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Deng, X. & Yu, Y. Automatic calibration of crack and flaking diseases in ancient temple murals. npj Herit. Sci. 10, 163 (2022).10.1186/s40494-022-00799-y ↗
2. Yang, W., Han, Y. & Yang, C. Diseases and preventive conservation of mural paintings in Tibetan Buddhist main halls in the Tumote area of Inner Mongolia (in Chinese). Chin. Overseas Architecture 5, 129–136 (2024).
3. Lyu, S., Mao, J. & Hou, M. Mural linear feature enhancement algorithm combining semi-supervised image segmentation and dimensionality reduction. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XLVI-M-1-2021, 423–427 (2021).10.5194/isprs-archives-XLVI-M-1-2021-423-2021 ↗
4. Gao, Z. et al. Application of hyperspectral imaging technology to digitally protect murals in the Qutan temple. npj Herit. Sci. 11, 8 (2023).10.1186/s40494-022-00847-7 ↗
5. Hou, M. et al. Extraction of hidden information under sootiness on murals based on hyperspectral image enhancement. Appl. Sci. 9, 3591 (2019).10.3390/app9173591 ↗
6. Yang, R. Protection and re-restoration of the mural paintings in the Wanzhang Northern Dynasties tomb in Handan (in Chinese). China Cult. Herit. Sci. Res. 4, 61–67 (2009).
7. Dal Fovo, A. et al. Non-invasive mapping methods for pigments analysis of Roman mural paintings. J. Cult. Herit. 43, 311–318 (2020).10.1016/j.culher.2019.12.002 ↗
8. Koochakzaei, A., Mobasher Maghsoud, E. & Jelodarian Bidgoli, B. Non-invasive imaging and spectroscopy techniques for identifying historical pigments: a case study of Iranian manuscripts from the Qajar era. npj Herit. Sci. 11, 157 (2023).10.1186/s40494-023-01011-5 ↗
9. Zhang, Y. et al. In-situ and non-destructive analysis of pigment layers of mural paintings in the Xianrenya cave temple in Tianshui (in Chinese). Spectrosc. Spectr. Anal. 42, 3526–3532 (2022).
10. Tang, X. et al. Digital restoration of mural paintings from late Tang tomb M1373 in Xi’an based on hyperspectral analysis and image interaction processing. npj Herit. Sci. 13, 192 (2025).10.1038/s40494-025-01734-7 ↗
11. Zeng, Z. et al. Virtual restoration of ancient tomb murals based on hyperspectral imaging. npj Herit. Sci. 12, 410 (2024).10.1186/s40494-024-01501-0 ↗
12. Yang, W. et al. Virtual restoration of tomb mural pigment colors based on fusion spectral analysis (in Chinese). Sci. Conserv. Archaeol. 35, 11–23 (2023).
13. Qiao, K., Hou, M., Lyu, S. & Li, L. Extraction and restoration of scratched murals based on hyperspectral imaging—a case study of murals in the East Wall of the sixth grotto of Yungang Grottoes, Datong, China. npj Herit. Sci. 12, 123 (2024).10.1186/s40494-024-01215-3 ↗
14. Wang, S. et al. Virtual restoration of ancient mold-damaged paintings based on spectral-guided asymmetric autoencoder for hyperspectral images. npj Herit. Sci. 13, 533 (2025).10.1038/s40494-025-02103-0 ↗
15. Herens, E., Defeyt, C., Walter, P. & Strivay, D. Discovery of a woman portrait behind La Violoniste by Kees van Dongen through hyperspectral imaging. npj Herit. Sci. 5, 14 (2017).10.1186/s40494-017-0127-4 ↗
16. Pan, N. et al. Extracting faded mural patterns based on the combination of spatial–spectral feature of hyperspectral image. J. Cult. Herit. 27, 80–87 (2017).10.1016/j.culher.2017.02.017 ↗
17. Li, X., Yang, H., Chen, C., Zhao, G. & Ni, J. Deterioration identification of stone cultural heritage based on hyperspectral image texture features. J. Cult. Herit. 69, 57–66 (2024).10.1016/j.culher.2024.07.011 ↗
18. Taghipour, A. & Ghassemian, H. A bottom-up and top-down human visual attention approach for hyperspectral anomaly detection. J. Vis. Commun. Image Represent. 78, 103188 (2021).
19. Zaprzalska, D. et al. Revealing the unseen: advanced digital imaging and spectroscopy for the documentation and non-invasive analysis of a 16th-century Cypriot composite icon. Herit. Sci. 12, 170 (2024).10.1186/s40494-024-01282-6 ↗
20. Cabezos-Bernal, P. M., Rodriguez-Navarro, P. & Gil-Piqueras, T. Documenting paintings with gigapixel photography. J. Imaging 7, 156 (2021).10.3390/jimaging7080156 ↗
21. Maes, F., Collignon, A., Vandermeulen, D., Marchal, G. & Suetens, P. Multimodality image registration by maximization of mutual information. IEEE Trans. Med. Imaging 16, 187–198 (1997).10.1109/42.563664 ↗
22. Yan, L., Wang, Z. & Ye, Z. Multimodal image registration algorithm considering gray and gradient information (in Chinese). Acta Geodaetica et. Cartogr. Sin. 47, 71–81 (2018).
23. Li, J., Hu, Q. & Ai, M. RIFT: multi-modal image matching based on radiation-variation insensitive feature transform. IEEE Trans. Image Process. 29, 3296–3310 (2020).10.1109/TIP.2019.2959244 ↗
24. Geng, Z., Liu, H., Duan, P., Wei, X. & Li, S. Feature-based multimodal remote sensing image matching: benchmark and state-of-the-art. ISPRS J. Photogramm. Remote Sens. 229, 285–302 (2025).10.1016/j.isprsjprs.2025.08.028 ↗
25. Wallis, R. H. An approach to the space variant restoration and enhancement of images. In Proc. Symposium on Current Mathematical Problems in Image Science, 235–241, (Naval Postgraduate School, Monterey, CA, USA, 1976).
26. Soria, X., Li, Y., Rouhani, M. & Sappa, A. D. Tiny and efficient model for the edge detection generalization. In Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. 1364–1373 (IEEE, Paris, France, 2023).10.1109/ICCVW60793.2023.00147 ↗
27. Shi, J. & Tomasi, C. Good features to track. In Proc.IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 593–600 (IEEE, Seattle, WA, USA, 1994).10.1109/CVPR.1994.323794 ↗
28. Rublee, E., Rabaud, V., Konolige, K. & Bradski, G. ORB: an efficient alternative to SIFT or SURF. In Proc. IEEE International Conference on Computer Vision (ICCV). 2564–2571 (IEEE, Barcelona, Spain, 2011).10.1109/ICCV.2011.6126544 ↗
29. Cover, T. M. & Hart, P. E. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13, 21–27 (1967).10.1109/TIT.1967.1053964 ↗
30. Chum, O., Werner, T. & Matas, J. Two-view geometry estimation unaffected by a dominant plane. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). 772–779 (IEEE, San Diego, CA, USA, 2005).10.1109/CVPR.2005.354 ↗
31. Parzen, E. On estimation of a probability density function and mode. Ann. Math. Stat. 33, 1065–1076 (1962).10.1214/aoms/1177704472 ↗
32. Zhang, T. Y. & Suen, C. Y. A fast parallel algorithm for thinning digital patterns. Commun. Acm. 27, 236–239 (1984).10.1145/357994.358023 ↗
33. Lowe, D. G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004).10.1023/B:VISI.0000029664.99615.94 ↗
34. Sun, J., Shen, Z., Wang, Y., Bao, H. & Zhou, X. LoFTR: detector-free local feature matching with transformers. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 8922–8931 (IEEE, 2021).10.1109/CVPR46437.2021.00881 ↗
35. Revaud, J., Weinzaepfel, P., de Souza, C. R. & Humenberger, M. R2D2: repeatable and reliable detector and descriptor. Proc. Adv. Neural Inf. Process. Syst. (NeurIPS). 32, 12405–12415 (2019).
36. DeTone, D., Malisiewicz, T. & Rabinovich, A. SuperPoint: self-supervised interest point detection and description. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 224–236 (IEEE, Salt Lake City, UT, USA, 2018).10.1109/CVPRW.2018.00060 ↗
37. Sarlin, P.-E., DeTone, D., Malisiewicz, T. & Rabinovich, A. SuperGlue: learning feature matching with graph neural networks. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4937–4946 (IEEE, 2020).10.1109/CVPR42600.2020.00499 ↗
38. Wu, C., Chen, H., Du, B. & Zhang, L. Unsupervised change detection in multitemporal VHR images based on deep kernel PCA convolutional mapping network. IEEE Trans. Cybern. 52, 12084–12098 (2022).10.1109/TCYB.2021.3086884 ↗
39. Sony Corporation. ILCE-7RM5 (A7R V) digital camera specifications. Sony Corporation. Available at: https://www.sony.com (accessed 2026).
40. Sony Corporation. FE 90 mm F2.8 Macro G OSS (SEL90M28G) lens specifications. Sony Corporation. Available at: https://www.sony.com (accessed 2026).
41. Headwall Photonics. Hyperspec® VNIR/SWIR with Co-Registered Pixels hyperspectral imager: product specifications. Headwall Photonics, Inc. Available at: https://headwallphotonics.com (accessed 2026).