(49-6) 33 * << * >> * Russian * English * Content * All Issues

P-CVD-SWIN: a parameterized neural network for image daltonization
V.V. Volkov 1, P.V. Maximov 2, N.B. Alkzir 3,1,2, S.A. Gladilin 1,2, D.P. Nikolaev 1, I.P. Nikolaev 1,2

1 Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences,
119333, Russia, Moscow, Prospekt 60-letiia Oktiabria 9;
2 Institute for Information Transmission Problems of the Russian Academy of Sciences,
127051, Moscow, Russia, Bolshoy Karetny per. 19, build 1;
3 HSE University,
101000, Russia, Moscow, Myasnitskaya Ulitsa 20

 PDF, 3023 kB

DOI: 10.18287/COJ1140

Pages: 1164-1173.

Full text of article: English language.

Abstract:
Nowadays, about 8 % of men and 0.5 % of women worldwide suffer from color vision deficiency. People with color vision deficiency are mostly dichromats and closely related anomalous trichromats, and are subdivided into three types: protans, deutans, and tritans. Special image preprocessing methods referred to as daltonization techniques allow increasing the distinguishability of chromatic contrasts for people with dichromacy. State-of-the-art neural network architectures involve training separate models for each type of dichromacy, which makes such models cumbersome and inconvenient. In this paper, we propose for the first time a parameterized neural network architecture, which allows training the same neural network model for any type of dichromacy, being specified as a parameter. We named this model P-CVD-SWIN, supposing it a parametrized development of the recently suggested CVD-SWIN model. A generalization of the Vienot dichromacy simulation method was proposed for model training. Experiments have shown that the P-CVD-SWIN neural network parameterized by the type of dichromacy provides better preservation of chromatic naturalness during daltonization, compared to a combination of several CVD-SWIN models, each trained for its own type of dichromacy.

Keywords:
CVD precompensation, color vision deficiency, daltonization, image recoloring, neural network, SWIN-transformer.

Citation:
Volkov VV, Maximov PV, Alkzir NB, Gladilin SA, Nikolaev DP, Nikolaev IP. P-CVD-SWIN: a parameterized neural network for image daltonization. Computer Optics 2025; 49(6): 1164-1173. DOI: 10.18287/COJ1140.

References:
  1. Stockman A, Sharpe LT. The spectral sensitivities of the middle-and long-wavelength-sensitive cones derived from measurements in observers of known genotype. Vis Res 2000; 40: 1711-1737. DOI: 10.1016/S0042-6989(00)00021-3.
  2. Ribeiro M, Gomes AJ. Recoloring algorithms for colorblind people: A survey. ACM Comput Surv (CSUR). 2019; 52: 1-37. DOI: 10.1145/3329118.
  3. Al-Kazir NB, Yarykina MS, Nikolaev DP, Nikolaev IP. Development of Image Preprocessing Methods for Software Compensation of Refraction Anomalies of an Observer’s Eyes. Neurosc. Behav. Physiol. 2024; 54(9): 1-14. DOI: 10.1007/s11055-024-01745-0.
  4. Maximov PV, Maximova EM, Gracheva MA, Kazakova AA, Kulagin AS. The algorithm for simulation of dichromatic vision and its application for detecting color vision deficiencies [In Russian]. Sensornye Sist. 2019; 33(3): 181–196. DOI: 10.1134/S0235009219030053.
  5. Viénot F, Brettel H, Mollon JD. Digital video colourmaps for checking the legibility of displays by dichromats. Color Research & Application. 1999; 24: 243-252. DOI: 10.1002/(SICI)1520-6378(199908)24:4%3C243::AID-COL5%3E3.0.CO;2-3.
  6. Hu X, Zhang Z, Liu X, Wong TT. Deep visual sharing with colorblind. IEEE Transactions on Computational Imaging. 2019; 5(4): 649-59. DOI: 10.1109/TCI.2019.2908291.
  7. Ma Y, Gu X, Wang Y. Color discrimination enhancement for dichromats using self-organizing color transformation. Information Sciences. 2009; 179(6): P. 830–843. DOI: 10.1016/j.ins.2008.11.010.
  8. Tennenholtz G, Zachevsky I. Natural contrast enhancement for dichromats using similarity maps. 2016 IEEE International Conference on the Science of Electrical Engineering (ICSEE). 2016; 1–5. DOI: 10.1109/ICSEE.2016.7806183.
  9. Simon-Liedtke JT, Farup I. Multiscale daltonization in the gradient domain. Journal of Perceptual Imaging. 2018; 1(1): 10503–1. DOI: 10.2352/J.Percept.Imaging.2018.1.1.010503.
  10. Farup I. Individualised halo-free gradient-domain colour image daltonisation. Journal of Imaging. 2020; 6(11): 116. DOI: 10.3390/jimaging6110116.
  11. Bao S, Song X, Zhuang X, Lu M, Le G. Color correction method considering hue information for dichromats. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 2024. DOI: 10.1587/transfun.2024EAP1026.
  12. Sidorchuk D, Nurmukhametov A, Maximov P, Bozhkova V, Sarycheva A, Pavlova M, Kazakova A, Gracheva M, Nikolaev D. Leveraging Achromatic Component for Trichromat-Friendly Daltonization. J. Imaging. 2025; 11(7): 225. 10.3390/jimaging11070225.
  13. Sheshkus AV, Kondrashova AN, Nikolaev DP. Development of the Neural Network Based Recognition Methods at V.L. Arlazarov’s Scientific School. Pattern Recognit. Image Anal. 2023. 33(4): 717-729. DOI: 10.1134/S1054661823040417.
  14. Orii H, Kawano H, Suetake N, Maeda H. Color conversion for color blindness employing multilayer neural network with perceptual model. Image and Video Technology: 7th Pacific-Rim Symposium, PSIVT 2015. 2016: 3–14. DOI: 10.1007/978-3-319-29451-3_1.
  15. Li H, Zhang L, Zhang X, Zhang M, Zhu G, Shen P, Li P, Bennamoun M, Shah SA. Color vision deficiency datasets & recoloring evaluation using GANs. Multimedia Tools and Applications. 2020; 79: 27583–27614. DOI: 10.1007/s11042-020-09299-2.
  16. Welfert M, Kurri GR, Otstot K, Sankar L. Addressing GAN training instabilities via tunable classification losses. IEEE Journal on Selected Areas in Information Theory. 2024; DOI: 10.1109/JSAIT.2024.3415670.
  17. Pendhari N, Shaikh D, Shaikh N, Nagori AG. Comprehensive color vision enhancement for color vision deficiency: a tensorflow and keras based approach. ICTACT Journal on Image & Video Processing. 2024; 14(4). DOI: 10.21917/ijivp.2024.0467.
  18. Chen L, Zhu Z, Huang W, Go K, Chen X, Mao X. Image recoloring for color vision deficiency compensation using Swin transformer. Neural Computing and Applications. 2024; 36(11): 6051–6066. DOI: 10.1007/s00521-023-09367-2.
  19. Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B. Swin transformer: Hierarchical vision transformer using shifted windows. InProceedings of the IEEE/CVF international conference on computer vision. 2021; 10012-10022.
  20. Kraft TW, Neitz J, Neitz M. Spectra of human L cones. Vision Research. 1998; 38(23): 3663-3670. DOI: 10.1016/S0042-6989(97)00371-4.
  21. Stockman A, Sharpe LT. Human cone spectral sensitivities: a progress report. Vision Research. 1998; 38(21): 3193-3206. DOI: 10.1016/S0042-6989(98)00060-1.
  22. Zhu Z., Toyoura M., Go K., Kashiwagi K., Fujishiro I., Wong T.T., Mao X. Personalized image recoloring for color vision deficiency compensation. IEEE Transactions on Multimedia. 2021; 24: 1721-1734. DOI: 10.1109/TMM.2021.3070108.
  23. Hassan MF, Paramesran R. Naturalness preserving image recoloring method for people with red–green deficiency. Signal Process. Image Commun. 2017; 57: 126–133. DOI: 10.1016/j.image.2017.05.011.
  24. Wang X, Zhu Z, Chen X, Go K, Toyoura M, Mao X. Fast contrast and naturalness preserving image recolouring for dichromats. Comput. Graph. 2021; 98: 19–28. DOI: 10.1016/j.cag.2021.04.027.
  25. Zhu Z, Toyoura M, Go K, Fujishiro I, Kashiwagi K, Mao X. Processing images for red–green dichromats compensation via naturalness and information-preservation considered recoloring. Vis. Comput. 2019; 35(6): 1053–1066. DOI: 10.1007/s00371-019-01689-4.
  26. Zhu Z, Toyoura M, Go K, Fujishiro I, Kashiwagi K, Mao X. Naturalness- and information-preserving image recoloring for red–green dichromats. Signal Process. Image Commun. 2019; 76: 68–80. DOI: 10.1016/j.image.2019.04.004.
  27. Zhu Z, Mao X. Image recoloring for color vision deficiency compensation: A survey. Vis. Comput. 2021; 37(12): 2999–3018. DOI: 10.1007/s00371-021-02240-0.
  28. Konovalenko IA, Smagina AA, Nikolaev DP, Nikolaev PP. ProLab: A perceptually uniform projective color coordinate system. IEEE Access. 2021; 9: 133023–133042. DOI: 10.1109/ACCESS.2021.3115425.
  29. Machado GM, Oliveira MM. Real-time temporal-coherent color contrast enhancement for dichromats. Comput. Graph. Forum. 2010; 29(3): 933–942. DOI: 10.1111/j.1467-8659.2009.01701.x.
  30. Basova O, Gladilin S, Kokhan V, Kharkevich M, Sarycheva A, Konovalenko I, Chobanu M, Nikolaev I. Evaluation of Color Difference Models for Wide Color Gamut and High Dynamic Range. J. Imaging. 2024; 10(12): 317. DOI: 10.3390/jimaging10120317.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20