Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

DOI: http://dx.doi.org/10.15439/2025F9395

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 783–787 (2025)

Full text

Abstract. This paper addresses the challenge of data augmentation for monochrome images, which are still highly relevant in machine vision. Current augmentation methods designed for natural scenes focus on geometric transformation and often fall short in simulating real-world illumination variations. We propose a novel approach that leverages a two-step monochrome image processing technique consisting of image pseudo-colorization followed be a specific decolorization scheme. Our method generates diverse and unpredictable intensity variations, effectively emulating illumination changes and, if only a specific category of color maps are used, preserving the naturalness of the resulting images. To exclude the results which closely replicate images already in the dataset, we rank these maps, identifying a subset that significantly alters illumination characteristics of the originals. A popular SSIM measure is used for that purpose. This technique enhances the illumination diversity of datasets, offering a valuable tool for improving the robustness of AI/ML models.

References

1. A. Mumuni and F. Mumuni, “Data augmentation: A comprehensive survey of modern approaches,” Array, vol. 16, p. 100258, 2022. https://doi.org/10.1016/j.array.2022.100258. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2590005622000911
2. Y. Zhang, A. Yilmaz, M. Popa, and C. Brewster, “Analysis of the impact of data augmentation on the performance of deep learning models in multispectral food authenticity identification,” in Proc. 18th Conference on Computer Science and Intelligence Systems, ser. Annals of Computer Science and Information Systems, vol. 35. IEEE, 2023. https://dx.doi.org/10.15439/2023F3643 p. 823–832.
3. A. Mikolajczyk and M. Grochowski, “Data augmentation for improving deep learning in image classification problem,” in 2018 International Interdisciplinary PhD Workshop (IIPhDW), 2018. https://dx.doi.org/10.1109/IIPHDW.2018.8388338
4. L. Nanni, M. Paci, S. Brahnam, and A. Lumini, “Comparison of different image data augmentation approaches,” Journal of Imaging, vol. 7, no. 12, p. 222–239, 2014. https://dx.doi.org/10.3390/jimaging7120254
5. A. Śluzek, “Incremental image decolorization with randomizing factors,” in 32nd European Signal Processing Conference (EUSIPCO), 2024. https://dx.doi.org/10.23919/EUSIPCO63174.2024.10715444 pp. 591–595.
6. A. Śluzek, “An unorthodox technique for enhancing monochrome images of natural scenes,” in Proc. 6th Polish Conference on Artificial Intelligence, Katowice, Poland. Springer, 2025, in print.
7. A. Śluzek, “A new technique for enhanced monochrome visualization of non-visual data,” in Computational Science – ICCS 2025 Workshops, M. Paszynski, A. S. Barnard, and Y. J. Zhang, Eds. Springer Nature Switzerland, 2025, pp. 51–65.
8. C. Lu, L. Xu, and J. Jia, “Contrast preserving decolorization with perception-based quality metrics,” International Journal of Computer Vision, vol. 110, p. 222–239, 2014. https://dx.doi.org/10.1007/s11263-014-0732-6
9. N. S. Aghdam, M. M. Amin, M. E. Tavakol, and E. Ng, “Designing and comparing different color map algorithms for pseudo-coloring breast thermograms,” Journal of Medical Imaging and Health Informatics, vol. 3, no. 4, pp. 487–493, 2013. https://dx.doi.org/10.1166/jmihi.2013.1191
10. A. Rahimian, M. Etehadtavakol, M. Moslehi, and E. Ng, “Comparing different algorithms for the pseudo-coloring of myocardial perfusion single-photon emission computed tomography images,” Journal of Imaging, vol. 8, no. 12, p. 331, 12 2022. https://dx.doi.org/10.3390/jimaging8120331
11. Q. Liu, J. Xiong, L. Zhu, M. Zhang, and Y. Wang, “Extended RGB2Gray conversion model for efficient contrast preserving decolorization,” Multimedia Tools and Applications, vol. 76, p. 14055–14074, 2017. https://dx.doi.org/10.1007/s11042-016-3748-9
12. T. Wu, C. Eising, M. Glavin, and E. Jones, “An efficient and effective image decolorization algorithm based on cumulative distribution function,” Journal of Imaging, vol. 10, no. 3, 2024. https://dx.doi.org/10.3390/jimaging10030051
13. T. Wu and A. Toet, “Color-to-grayscale conversion through weighted multiresolution channel fusion,” Journal of Electronic Imaging, vol. 23, no. 4, p. 043004, 2014. https://dx.doi.org/10.1117/1.JEI.23.4.043004
14. J. Yu, F. Li, and X. Lv, “Contrast preserving decolorization based on the weighted normalized l1 norm,” Multimedia Tools and Applications, vol. 80, p. 31753–31782, 2021. https://dx.doi.org/10.1007/s11042-021-11172-9
15. M. Khan, Y. Gotoh, and N. Nida, “Medical image colorization for better visualization and segmentation,” in Medical Image Understanding and Analysis, M. Valdés Hernández and V. González-Castro, Eds. Cham: Springer International Publishing, 2017. https://dx.doi.org/10.1007/978-3-319-60964-5_50 pp. 571–580.
16. K. Moreland, “Why we use bad color maps and what you can do about it,” in Proc. IS&T Int’l. Symp. on Electronic Imaging: Human Vision and Electronic Imaging, vol. 28, 2016. https://dx.doi.org/10.2352/ISSN.2470-1173.2016.16.HVEI-133
17. “Colormap catalog,” accessed on Jan. 5, 2025. [Online]. Available: https://cmap-docs.readthedocs.io/en/latest/catalog/
18. J. Xiao, J. Hays, K. Ehinger, A. Oliva, and A. Torralba, “SUN database: Large-scale scene recognition from abbey to zoo,” in 2010 IEEE Conference CVPR, 2010. https://dx.doi.org/10.1109/CVPR.2010.5539970 pp. 3485–3492.
19. Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004. https://dx.doi.org/10.1109/TIP.2003.819861