SSA-based adaptive infrared-visible image fusion for ink enhancement in ancient bamboo slips
Source abstract
Abstract
Jiandu, ancient China’s primary writing medium before paper, frequently exhibits severe inscription degradation due to prolonged burial, making the texts difficult to decipher. To enhance textual visibility, this study proposes an adaptive infrared-visible image fusion method driven by Salient Spatial Attention (SSA), integrating the complementary strengths of both modalities to produce images with clear ink, texture, and color. First, an SSA module selectively enhances infrared ink features via adaptive feature selection, improving the visibility of faint inscriptions. Second, a multi-scale information measurement strategy ensures balanced representation of material texture and ink details. Finally, a tailored unsupervised loss function eliminates reliance on ground-truth images while preserving authentic visual characteristics. Experimental results demonstrate that the proposed approach outperforms existing methods, particularly in preserving text details, material texture, and color fidelity. The resulting enhanced images offer valuable support for cultural-heritage preservation and Jiandu research.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cultural Heritage Materials Analysis · Image Enhancement Techniques · Generative Adversarial Networks and Image Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (52)
Show source-provided references
1. Yu, X.Language and State: A Theory of the Progress of Civilization 2nd edn (FriesenPress, 2021).
2. Allen, S. M., Zuzao, L., Xiaolan, C. & Bos, J. History and Cultural Heritage of Chinese Calligraphy, Printing and Library Work: Edited By Susan M. Allen…[Et Al.] (IFLA publications, 141) (De Gruyter, 2010).10.1515/9783598441790 ↗
3. Ge, C. A re-understanding of the Silk Road reflected by the Han slips from Xuanquan, Dunhuang. The Western Regions Studies (2), 107–113 (2017).
4. Zhao, G. & Jia, L. Protection and requirements in the process of bamboo slip image information collection. Excav. Lit. (1), 13–19 (2023).
5. Bai, G., Song, P. & Zhang, X. An overview of the application of technology for clarity extraction of fuzzy information in cultural relics. Fujian Cultural Relics and Museology (4), 91–96 (2022).
6. Na, Z., Lujun, C. & Xuben, W. A method for archaeological text restoration and recognition based on horizontal and vertical projection. Sci. Technol. Bull. 30, 185–187 (2014).
7. Jinquan, L., Na, Z. & Xuben, W. Research on bamboo slip text image processing based on threshold segmentation. Sci. Technol. Bull. 28, 128–129+132 (2012).
8. Yangjie, Z.Application of Threshold-Based Image Segmentation Technology in Bamboo Slips. Master’s thesis, Chengdu University of Technology (2010).
9. Liuyan, W. & Xuben, W. Application of multi-scale retinex algorithm in bamboo slip image enhancement. Comput. Sci. 36, 288–290 (2009).10.1063/1.3156527 ↗
10. Zhang, W., Wang, X. & Jin, P. Application of Canny edge operator in bamboo slip text restoration. Microcomp. Inf. (9), 241–242 (2008).
11. Qin, Q., Wang, X. & Jiang, W. Application of unsharp masking method in bamboo slip text enhancement. Microcomp. Inf. (3), 241–242 (2008).
12. Na, Z.Research on Bamboo Slip Image Enhancement and Segmentation. Master’s thesis, Chengdu University of Technology (2007).
13. Li, S., Kang, X., Fang, L., Hu, J. & Yin, H. Pixel-level image fusion: a survey of the state of the art. Inf. Fusion 33, 100–112 (2017).10.1016/j.inffus.2016.05.004 ↗
14. Li, H., Wu, X.-J. & Kittler, J. Mdlatlrr: a novel decomposition method for infrared and visible image fusion. IEEE Trans. Image Process. 29, 4733–4746 (2020).10.1109/TIP.2020.2975984 ↗
15. Chen, J., Li, X., Luo, L., Mei, X. & Ma, J. Infrared and visible image fusion based on target-enhanced multiscale transform decomposition. Inf. Sci. 508, 64–78 (2020).10.1016/j.ins.2019.08.066 ↗
16. Liu, Y., Jin, J., Wang, Q., Shen, Y. & Dong, X. Region level based multi-focus image fusion using quaternion wavelet and normalized cut. Signal Process. 97, 9–30 (2014).10.1016/j.sigpro.2013.10.010 ↗
17. Bavirisetti, D. P. & Dhuli, R. Two-scale image fusion of visible and infrared images using saliency detection. Infrared Phys. Technol. 76, 52–64 (2016).10.1016/j.infrared.2016.01.009 ↗
18. Li, S., Yin, H. & Fang, L. Remote sensing image fusion via sparse representations over learned dictionaries. IEEE Trans. Geosci. remote Sens. 51, 4779–4789 (2013).10.1109/TGRS.2012.2230332 ↗
19. Liu, Y., Chen, X., Ward, R. K. & Wang, Z. J. Image fusion with convolutional sparse representation. IEEE Signal Process. Lett. 23, 1882–1886 (2016).10.1109/LSP.2016.2618776 ↗
20. Cvejic, N., Lewis, J., Bull, D. & Canagarajah, N. Region-based multimodal image fusion using ica bases. In Proc. International Conference on Image Processing, 1801–1804 (IEEE, 2006).10.1109/ICIP.2006.312638 ↗
21. Li, H., Liu, L., Huang, W. & Yue, C. An improved fusion algorithm for infrared and visible images based on multi-scale transform. Infrared Phys. Technol. 74, 28–37 (2016).10.1016/j.infrared.2015.11.002 ↗
22. Ma, J., Chen, C., Li, C. & Huang, J. Infrared and visible image fusion via gradient transfer and total variation minimization. Inf. Fusion 31, 100–109 (2016).10.1016/j.inffus.2016.02.001 ↗
23. Ma, J., Zhou, Z., Wang, B. & Zong, H. Infrared and visible image fusion based on visual saliency map and weighted least square optimization. Infrared Phys. Technol. 82, 8–17 (2017).10.1016/j.infrared.2017.02.005 ↗
24. Hou, R. et al. Infrared and visible images fusion using visual saliency and optimized spiking cortical model in non-subsampled shearlet transform domain. Multimed. Tools Appl. 78, 28609–28632 (2019).10.1007/s11042-018-6099-x ↗
25. Zhang, H., Xu, H., Tian, X., Jiang, J. & Ma, J. Image fusion meets deep learning: a survey and perspective. Inf. Fusion 76, 323–336 (2021).10.1016/j.inffus.2021.06.008 ↗
26. Li, H., Wu, X.-J. & Kittler, J. Rfn-nest: An end-to-end residual fusion network for infrared and visible images. Inf. Fusion 73, 72–86 (2021).10.1016/j.inffus.2021.02.023 ↗
27. Ram Prabhakar, K., Sai Srikar, V. & Venkatesh Babu, R. Deepfuse: a deep unsupervised approach for exposure fusion with extreme exposure image pairs. In Proc. IEEE International Conference On Computer Vision 4714–4722 (2017).10.1109/ICCV.2017.505 ↗
28. Li, H. & Wu, X.-J. Densefuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28, 2614–2623 (2019).10.1109/TIP.2018.2887342 ↗
29. Li, H., Wu, X.-J. & Durrani, T. S. Nestfuse: an infrared and visible image fusion architecture based on nest connection and spatial/channel attention models. IEEE Trans. Instrum. Meas. 69, 9645–9656 (2020).10.1109/TIM.2020.3005230 ↗
30. Zhang, H., Xu, H., Xiao, Y., Guo, X. & Ma, J. Rethinking the image fusion: a fast unified image fusion network based on proportional maintenance of gradient and intensity. In Proc. AAAI Conference on Artificial Intelligence 12797–12804 (AAAI, 2020).10.1609/aaai.v34i07.6975 ↗
31. Tang, L., Yuan, J. & Ma, J. Image fusion in the loop of high-level vision tasks: a semantic-aware real-time infrared and visible image fusion network. Inf. Fusion 82, 28–42 (2022).10.1016/j.inffus.2021.12.004 ↗
32. Tang, L., Yuan, J., Zhang, H., Jiang, X. & Ma, J. Piafusion: a progressive infrared and visible image fusion network based on illumination aware. Inf. Fusion 83, 79–92 (2022).10.1016/j.inffus.2022.03.007 ↗
33. Ma, J., Tang, L., Xu, M., Zhang, H. & Xia, G. Stdfusionnet: an infrared and visible image fusion network based on salient target detection. IEEE Trans. Instrum. Meas. 70, 1–13 (2021).
34. Xu, H., Ma, J., Jiang, J., Guo, X. & Ling, H. U2fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44, 502–518 (2020).10.1109/TPAMI.2020.3012548 ↗
35. Ma, J., Yu, W., Liang, P., Li, C. & Jiang, J. Fusiongan: a generative adversarial network for infrared and visible image fusion. Inf. Fusion 48, 11–26 (2019).10.1016/j.inffus.2018.09.004 ↗
36. Ma, J., Xu, H., Jiang, J., Mei, X. & Zhang, X.-P. Ddcgan: a dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans. Image Process. 29, 4980–4995 (2020).10.1109/TIP.2020.2977573 ↗
37. Tang, W., Yang, S., Niu, Y. & Sun, Z. Attentionfgan: infrared and visible image fusion using attention-based generative adversarial networks. Inf. Fusion 67, 88–100 (2021).
38. Zhang, Y. et al. Ifcnn: a general image fusion framework based on convolutional neural network. Inf. Fusion 54, 99–118 (2020).10.1016/j.inffus.2019.07.011 ↗
39. Li, W., Zhang, Y., Wang, G., Lu, W. & Gao, F. Dfenet: a dual-branch feature enhanced network integrating transformers and convolutional feature learning for multimodal medical image fusion. Biomed. Signal Process. Control 80, 104402 (2023).10.1016/j.bspc.2022.104402 ↗
40. Li, H. & Wu, X.-J. Crossfuse: a novel cross attention mechanism based infrared and visible image fusion approach. Inf. Fusion 103, 102147 (2024).10.1016/j.inffus.2023.102147 ↗
41. Zhao, Z. et al. Ddfm: denoising diffusion model for multi-modality image fusion. In Proc. IEEE/CVF International Conference on Computer Vision 8082–8093 (IEEE, 2023).10.1109/ICCV51070.2023.00742 ↗
42. Yue, J., Fang, L., Xia, S., Deng, Y. & Ma, J. Dif-fusion: toward high color fidelity in infrared and visible image fusion with diffusion models. IEEE Trans. Image Process. 32, 5705–5720 (2023).10.1109/TIP.2023.3322046 ↗
43. Yang, B. et al. Lfdt-fusion: a latent feature-guided diffusion transformer model for general image fusion. Inf. Fusion 113, 102639 (2025).10.1016/j.inffus.2024.102639 ↗
44. Xue, L., Meng-lei, W., Yuan, L. & Yi-chen, Z. Nondestructive techniques in the research and preservation of cultural relics. Spectrosc. Spectr. Anal. 38, 2026–2031 (2018).
45. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference On Computer Vision And Pattern Recognition 770–778 (IEEE, 2016).10.1109/CVPR.2016.90 ↗
46. Wang, Z., Bovik, A. C., Sheikh, H. R. & Simoncelli, E. P. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004).10.1109/TIP.2003.819861 ↗
47. Qu, G., Zhang, D. & Yan, P. Information measure for performance of image fusion. Electron. Lett. 38, 313–315 (2002).10.1049/el:20020212 ↗
48. Sharma, G., Wu, W. & Dalal, E. N. The ciede2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Res. Appl. 30, 21–30 (2005).10.1002/col.20070 ↗
49. Li, J., Jiang, J., Liang, P., Ma, J. & Nie, L. Maefuse: Transferring omni features with pretrained masked autoencoders for infrared and visible image fusion via guided training. In Proc. IEEE Transactions on Image Processing (IEEE, 2025).10.1109/TIP.2025.3541562 ↗
50. Yao, L. A study on the rejoining and interpretation of the new Juyan slips. Huaxia Archaeol. 154–160 (2023).
51. Tang, L., Li, C. & Ma, J. Mask-difuser: a masked diffusion model for unified unsupervised image fusion. In Proc. IEEE Transactions on Pattern Analysis and Machine Intelligence 1–18 (IEEE, 2025).10.1109/TPAMI.2025.3609323 ↗
52. López-Baldomero, A. B. et al. Hyperspectral dataset of historical documents and mock-ups from 400 to 1700 nm (hyperdoc). Sci. Data 12, 1248 (2025).10.1038/s41597-025-05599-0 ↗