SavedAdd your journal

Journals / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi / 2025 / Cilt: 14 Sayı: 4

Performance comparison of different Retinex methods on enhancement of low light cave images

Düşük ışıklı mağara görsellerinin iyileştirilmesinde farklı Retineks yöntemlerinin performans karşılaştırması

Bilgin Yazlık(NEVŞEHİR HACI BEKTAŞ VELİ ÜNİVERSİTESİ)0000-0002-8172-3192
Egemen Nazife Yazlık(NEVŞEHİR ÜNİVERSİTESİ, MESLEK YÜKSEKOKULU)0000-0003-2830-3700
Pages
1625–1637
Publication Date
2025-10-15
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

While BIMEF is recommended for applications requiring general image enhancement and structural consistency, MSRETINEX and LIME can be preferred in applications requiring high dynamic range and detail preservation.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Caves are spaces that open into the earth and are often either completely dark or receive very little light.
📊
Key Findings & Data:A cave image dataset consisting of 82 low-light images is used for quantitative analysis.
💡
Conclusion & Impact:While BIMEF is recommended for applications requiring general image enhancement and structural consistency, MSRETINEX and LIME can be preferred in applications requiring high dynamic range and detail preservation.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Retineks · mağara · görüntü iyileştirme

Abstract

Caves are spaces that open into the earth and are often either completely dark or receive very little light. Photographs taken inside caves are usually subject to extremely low light conditions and image quality is negatively affected. In this study, state-of-the-art Retinex-based image enhancement methods are used to enhance the quality of images taken in the cave. Enhanced images are evaluated both quantitatively and qualitatively. A cave image dataset consisting of 82 low-light images is used for quantitative analysis. The enhanced results from all methods are visually compared using three sample images from the dataset for qualitative analysis. Eleven different image quality assessment methods are applied for quantitative analysis. The results of the study show that Retinex-based methods are successful in the enhancement of low-light cave images. While BIMEF is recommended for applications requiring general image enhancement and structural consistency, MSRETINEX and LIME can be preferred in applications requiring high dynamic range and detail preservation. In cases where noise reduction and objective quality assessment metrics are at the forefront, SRIE provides advantages.

Özet

Mağaralar dünyanın içine açılan, çoğunlukla ya tamamen ışıksız ya da çok az ışık alan mekanlardır. Mağaraların içinde çekilen fotoğraflar genellikle çok düşük ışık koşullarına maruz kalır ve görsel kaliteleri olumsuz etkilenir. Bu çalışmada, mağarada çekilen görüntülerin kalitesini iyileştirmek için güncel Retinex tabanlı görüntü iyileştirme yöntemleri kullanılmıştır. İyileştirilen görüntüler hem nicel hem de nitel olarak değerlendirilmiştir. Nicel analiz için 82 adet düşük ışık görüntüsünden oluşan bir mağara görüntü veri seti kullanılmıştır. Nitel analiz için tüm yöntemlerin iyileştirme sonuçları, veri setinden seçilen üç örnek görüntü ile görsel olarak karşılaştırılmıştır. On bir farklı görüntü kalitesi değerlendirme yöntemi nicel analiz için uygulanmıştır. Çalışmanın sonuçları, Retinex tabanlı yöntemlerin düşük ışıklı mağara görüntülerini iyileştirmede başarılı olduğunu göstermektedir. Genel görüntü iyileştirme ve yapısal tutarlılık gerektiren uygulamalar için BIMEF önerilirken, yüksek dinamik aralık ve detay korunması gereken uygulamalarda MSRETINEX ve LIME tercih edilebilir. Gürültü azaltma ve nesnel kalite değerlendirme metriklerinin ön planda olduğu durumlarda SRIE avantaj sağlamaktadır.

🔖

Cite This Article

Yazlık, B., Yazlık, E. N. (2025). Performance comparison of different Retinex methods on enhancement of low light cave images. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 14 Sayı: 4, 1625–1637. https://doi.org/10.28948/ngumuh.1776861

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (30)

  1. D. Ford and P. Williams, Karst Hydrogeology and Geomorphology. John Wiley and Sons, 2007. doi: 10.1002/9781118684986.
  2. E. H. Land and J. J. McCann, Lightness and retinex theory. Journal of the Optical Society of America, 61, 1–11, 1971. doi: 10.1364/JOSA.61.000001.
  3. T. Gao and P. Tao, A comprehensive review of low-light image enhancement techniques. International Conference on Image Processing, Computer Vision and Machine Learning, 158–170, 2024. doi: 10.1109/ICICML63543.2024.10957894.
  4. E. H. Land, An alternative technique for the computation of the designator in the retinex theory of color vision. Proceedings of the National Academy of Sciences, 83, 3078–3080, 1986. doi: 10.1073/pnas.83.10.3078.
  5. A. Hurlbert, Formal connections between lightness algorithms. Journal of the Optical Society of America, 1684–1693, 1986. doi: 10.1364/JOSAA.3.001684.
  6. Z. Rahman, D. J. Jobson, and G. A. Woodell, Retinex processing for automatic image enhancement. Journal of Electronic Imaging, 13, 100–110, 2004. doi: 10.1117/1.1636183.
  7. A. Moore, J. Allman, G. Fox and R. Goodman, A VLSI Neural Network for Color Constancy, Advances in Neural Information Processing Systems 3, Morgan Kaufmann, 1990.
  8. B. Petro, C. Sbert, and J. M. Morel, Multiscale retinex. Image Processing Online, 71–88, 2014. doi: 10.5201/ipol.2014.107.
  9. F. Katırcıoğlu, Düşük-ışıklı renkli görüntülerin iyileştirilmesinde kullanılan retineks algoritmalarının karşılaştırmalı analizi. Mühendislik Bilimleri ve Araştırmaları Dergisi, 3, 188-206, 2021. doi: 10.46387/bjesr.955356.
  10. Z. Ying, G. Li and W. Gao, A bio-inspired multi-exposure fusion framework for low-light image enhancement. arXiv, 2017. doi: 10.48550/arXiv.1711.00591.
  11. H. Fu, W. Zheng, X. Meng, X. Wang, C. Wang, and H. Ma, You do not need additional priors or regularizers in retinex-based low-light image enhancement. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18125–18134, Vancouver, BC, Canada, 2023. doi: 10.1109/CVPR52729.2023.01738.
  12. X. Xu, K. Zhou, T. Hu, R. Wang, and H. Bao, Low-light video enhancement via spatial-temporal consistent illumination and reflection decomposition. arXiv, 2024. doi: 10.48550/arXiv.2405.15660.
  13. X. Guo, Y. Li, and H. Ling, LIME: Low-light image enhancement via illumination map estimation. IEEE Transactions on Image Processing, 26, 982–993, 2017. doi: 10.1109/TIP.2016.2639450.
  14. X. Zhou, J. Guo, H. Liu, and C. Wang, A fusion-based and multi-layer method for low light image enhancement. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1–5, Rhodes Island, Greece, 2023. doi: 10.1109/ICASSP49357.2023.10096454.
  15. Z. Mahmood, N. Muhammad, N. Bibi, Y. M. Malik, and N. Ahmed, Human visual enhancement using multi scale retinex. Informatics in Medicine Unlocked, 13, 9–20, 2018. doi: 10.1016/j.imu.2018.09.001.
  16. P. Joshi and S. Prakash, Image enhancement with naturalness preservation. The Visual Computer, 36, 71–83, 2020. doi: 10.1007/s00371-018-1587-6.
  17. X. Fu, D. Zeng, Y. Huang, X. P. Zhang and X. Ding, A weighted variational model for simultaneous reflectance and illumination estimation. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2782–2790. Las Vegas, NV, USA, 2016. doi: 10.1109/CVPR.2016.304.
  18. Y. H. Liu, K. F. Yang and H. M. Yan, No-reference image quality assessment method based on visual parameters. Journal of Electronic Science and Technology, 17, 171–184, 2019. doi: 10.11989/JEST.1674-862X.70927091.
  19. T. Stathaki, Image Fusion: Algorithms and Applications. Elsevier, 2011.
  20. E. Shannon, A mathematical theory of communication. Bell System Technical Journal, 27, 379–423, 1948. doi: 10.1002/j.1538-7305.1948.tb01338.x.
  21. D. Y. Tsai, Y. Lee and E. Matsuyama, Information entropy measure for evaluation of image quality. Journal of Digital Imaging, 21, 338–347, 2008. doi: 10.1007/s10278-007-9044-5.
  22. I. Avcibas, B. Sankur and K. Sayood, Statistical evaluation of image quality measures. Journal of Electronic Imaging, 11, 206–223, 2002. doi: 10.1117/1.1455011.
  23. H. Alan and C. Bovik, A visual information fidelity approach to video quality assessment. The First International Workshop on Video Processing And Quality Metrics for Consumer Electronics, 2117–2128, 2005. https://live.ece.utexas.edu/publications/2005/hrs_vidqual_vpqm2005.pdf.
  24. W. Xue, L. Zhang, X. Mou and A. C. Bovik, Gradient magnitude similarity deviation: a highly efficient perceptual image quality index. IEEE Transactions on Image Processing, 23, 684–695, 2014. doi: 10.1109/TIP.2013.2293423.
  25. Mathworks. Mean-Squared Error User's Guide (r2014b). Retrieved October 6, 2025 from https://www.mathworks.com/help/images/ref/immse.html.
  26. Z. Wang, A. Bovik, H. Sheikh and E. Simoncelli, Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13, 600–612, 2004. doi: 10.1109/TIP.2003.819861.
  27. Z. Wang, E. Simoncelli and A. Bovik, Multiscale structural similarity for image quality assessment. The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers, pp. 1398-1402, Pacific Grove, CA, USA, 2003. doi: 10.1109/ACSSC.2003.1292216.
  28. U. Sara, M. Akter and M. Uddin, Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. Journal of Computer and Communications, 7, 8-18, 2019. doi: 10.4236/jcc.2019.73002.
  29. A. Mittal, R. Soundararajan and A. Bovik, Making a ‘completely blind’ image quality analyzer. IEEE Signal Processing Letters, 20, 209–212, 2013. doi: 10.1109/LSP.2012.2227726.
  30. N. Venkatanath, D. Praneeth, M. Chandrasekhar, S. Channappayya and S. Medasani, Blind image quality evaluation using perception-based features. Twenty First National Conference on Communications, pp. 1–6, Mumbai, India, 2015. doi: 10.1109/NCC.2015.7084843