Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Low-light facial images often suffer from reduced visibility, noise, color distortion, and loss of structural information, which can degrade subsequent face-analysis performance. This study proposes a perception-guided framework for single-image low-light facial enhancement based on Retinex-inspired illumination–reflectance decomposition and spatially adaptive enhancement. Local contrast and luminance-masking cues are incorporated through a Perception Contrast Optimization Module (PCOM) to regulate enhancement intensity across differently illuminated regions. Illumination correction, perception-guided adaptive fusion, and edge-preserving post-processing are subsequently applied to improve facial visibility while maintaining relevant structural information. Experiments were conducted on a held-out set of 900 DARK FACE images using no-reference image-quality assessment and downstream face-analysis tasks. Enhancement reduced the mean NIQE score from 4.8652 to 4.7828. Using a fixed YOLOv8-Face detector, AP@0.50 increased from 16.80% to 26.22%, while mAP@0.50:0.95 increased from 4.99% to 7.82%. In binary Face/Non-Face classification, ImageNet-pretrained EfficientNet-B0 achieved 95.22% accuracy and 99.08% recall on enhanced samples, compared with 95.69% accuracy and 91.74% recall on the corresponding original samples. The results demonstrate that the proposed enhancement substantially improves downstream face detectability and Face recall under challenging low-light conditions. However, a trade-off is observed in some perceptual-quality and precision measures.

Keywords

Low-light image enhancement Face detection Retinex-inspired enhancement Perception-guided enhancement DARK FACE EfficientNet-B0

Article Details

How to Cite
Al-Tamimi, M. S. H., Abed Alah, R. S., & Adnan, S. R. (2026). Perception-guided Retinex-inspired framework for low-light facial image enhancement and robust face analysis. Future Technology, 6(1), 1–13. Retrieved from https://fupubco.com/futech/article/view/1182
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. M. M. Tatana, M. S. T., and Maswanganyi, R. C., “Low-Light Image and Video Enhancement for More Robust Computer Vision Tasks: A Review,” Journal of Imaging, vol. 11, no. 4, pp. 11040125, 2025. DOI: https://doi.org/10.3390/jimaging11040125.
  2. Y. Fan, Y. Wang, D. Liang, Y. Chen, H. Xie, F. L. Wang, J. L., and Wei, M., “Low-FaceNet: Face Recognition- Driven Low-Light Image Enhancement,” IEEE Transactions on Instrumentation and Measurement, vol. 73, no. 5019413, pp. 5019413, 2024. DOI: https://doi.org/10.1109/TIM.2024.3372230.
  3. Q. Zhao, G. Li, B. He, R. S., “Deep Learning for Low-Light Vision: A Comprehensive Survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 9, pp. 3566647, 2025. DOI: https://doi.org/10.1109/TNNLS.2025.3566647.
  4. Liu, F., and Fan, L., “A review of advancements in low-light image enhancement using deep learning,” Neurocomputing, vol. 652, pp. 131052, 2025. DOI: https://doi.org/10.1016/j.neucom.2025.131052.
  5. Bai, J., Yin, Y., He, Q., Li, Y., and Zhang, X., RetinexMamba: Retinex-Based Mamba for Low-Light Image Enhancement, 2024. DOI: https://doi.org/https://doi.org/10.1007/978-981-96-6596-9_30.
  6. Tian, Z., Qu, P., Li, J., Sun, Y., Li, G., Liang, Z., Zhang, W., “A Survey of Deep Learning-Based Low-Light Image Enhancement,” Sensors, vol. 23, no. 18, pp. 23187763, 2023. DOI: https://doi.org/https://doi.org/10.3390/s23187763.
  7. Liu, M., Li, X., and Fang, Y., “Low-Light Image Enhancement via Dual Information-Based Networks,” Electronics, vol. 13, no. 18, pp. 13183713, 2024. DOI: https://doi.org/https://doi.org/10.3390/electronics13183713.
  8. J. Zhan, E. S. G., and M. S. Sunar, “Low-light image enhancement: A comprehensive review on methods, datasets and evaluation metrics,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 10, pp. 102234, 2024. DOI: https://doi.org/https://doi.org/10.1016/j.jksuci.2024.102234.
  9. Y. Feng, S. Hou, H. Lin, Y. Zhu, P. Wu, W. Dong, J. Sun, Q. Y., and Zhang, Y., “DiffLight: Integrating Content and Detail for Low-light Image Enhancement,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024, pp. 6152.
  10. Jiang, Y., Zhu, J., Li, L., Ma, H., “A Joint Network for Low-Light Image Enhancement Based on Retinex,” Cognitive Computation, vol. 16, pp. 12559, 2024. DOI: https://doi.org/https://doi.org/10.1007/s12559-024-10347-4.
  11. R. Weng, Y. Zhang, H. Wu, W. Wang, D. W., “The Retinex enhancement algorithm for low-light intensity image based on improved illumination map,” IET Image Processing, vol. 18, no. 12, pp. 13180, 2024. DOI: https://doi.org/https://doi.org/10.1049/ipr2.13180.
  12. Yang, W., Yuan, Y., Ren, W., Liu, J., Scheirer, W.J., Wang, Z., Zhang, T., Zhong, Q., Xie, D., Pu, S., Zheng, Y., “Advancing image understanding in poor visibility environments: A collective benchmark study,” IEEE Transactions on Image Processing, vol. 29, pp. 5752, 2020. DOI: https://doi.org/10.1109/TIP.2020.2981922.
  13. Wang, Xiaofeng, Liang Huang, Mingxuan Li, Chengshan Han, Xin Liu, T. N., “Fast, Zero-Reference Low-Light Image Enhancement with Camera Response Model,” Sensors, vol. 24, no. 15, pp. 5019, 2024. DOI: https://doi.org/https://doi.org/10.3390/s24155019.
  14. M. Tan, Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” In Proceedings of the 36th International Conference on Machine Learning (ICML), 2019, pp. 6105–6114.
  15. J. Wu, B. Ding, B. Zhang, J. D., “A Retinex-based network for image enhancement in low-light environments,” PLOS ONE, vol. 19, no. 5, pp. e303696, 2024. DOI: https://doi.org/https://doi.org/10.1371/journal.pone.0303696.
  16. X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, M. P., “A review of convolutional neural networks in computer vision,” Artificial Intelligence Review, vol. 57, pp. 99, 2024. DOI: https://doi.org/https://doi.org/10.1007/s10462-024-10721-6.
  17. J. Cao, B. Peng, M. Gao, H. Hao, X. L. H. M., “Object Detection Based on CNN and Vision- Transformer: A Survey,” IET Computer Vision, vol. 19, no. 1, pp. e70028, 2025. DOI: https://doi.org/https://doi.org/10.1049/cvi2.70028.
  18. O. E. Olorunshola, P. O. Jemitola, A. K. A., “Comparative Study of Some Deep Learning Object Detection Algorithms: R-CNN, FAST R-CNN, FASTER R-CNN, SSD, and YOLO,” Nile Journal of Engineering and Applied Science, vol. 1, no. 1, pp. 70–80, 2023. DOI: https://doi.org/https://doi.org/10.5455/NJEAS.150264.
  19. J. Xu, Y. Qian, K. Wang, C. Liu, J. L., “Low-light face detection method based on the cross fusion of high-and low-frequency channel features,” CAAI Transactions on Intelligent Systems, vol. 19, no. 2, pp. 472–481, 2024. DOI: https://doi.org/https://doi.org/10.11992/tis.202208034.
  20. Kim M, Jung Y, L. S., “Attention Retinex Network (A4R-Net) for face detection under low-light environment,” ICT Express, vol. 10, no. 6, pp. 1206–12011, 2024. DOI: https://doi.org/https://doi.org/10.1016/j.icte.2024.09.009.
  21. Z. Li, Y. Bai, X. Wang, L. Huang, C. Lin, S. L., “Low illumination face detection based on image enhancement,” Journal of Computer Applications, vol. 44, no. 8, pp. 2588–2594, 2024.
  22. Li, P., “Multi-model fusion of DSFD and Zero-DCE for low-light face detection,” Applied and Computational Engineering, vol. 86, pp. 20241584, 2024. DOI: https://doi.org/https://doi.org/10.54254/2755- 2721/86/20241584.
  23. Liang, J., Wang, J., Quan, Y., Chen, T., Liu, J., Ling, H., and Xu, Y., “Recurrent exposure generation for low-light face detection,” IEEE Transactions on Multimedia, vol. 24, pp. 1609–1621, 2021.
  24. F. Kasim, T. E. Boult, R. Mora, B. Biesseck, R. Ribeiro, J. Schlueter, T. Repák, R. Vareto, D. Menotti, W. R. Schwartz, M. G., “Watchlist Challenge: 3rd Open-set Face Detection and Identification,” Proceedings of the 2024 IEEE International Joint Conference on Biometrics (IJCB), 2024, pp. 1–10. DOI: https://doi.org/https://doi.org/10.1109/IJCB62174.2024.10744535.
  25. A. Alashbi, A. H. H. M. Mohamed, A. A. El-Saleh, I. Shayea, M. S. Sunar, Z. R. Alqahtani, F. Saeed, B. S., “Human face localization and detection in highly occluded unconstrained environments,” Engineering Science and Technology, an International Journal, vol. 61, pp. 101893, 2025. DOI: https://doi.org/https://doi.org/10.1016/j.jestch.2024.101893.
  26. L. Liu, G. Wang, Q. M., “ADYOLOv5-Face: An Enhanced YOLO-Based Face Detector for Small Target Faces,” Electronics, vol. 13, no. 21, pp. 4184, 2024. DOI: https://doi.org/https://doi.org/10.3390/electronics13214184.
  27. Zhang Y, Jiang J, Wang Z, Zhang Q, Jiang Y, Liu J, H. Z., “Low-light image enhancement method based on retinex theory and dual-tree complex wavelet transform,” Journal of King Saud University Computer and Information Sciences, vol. 37, no. 5, pp. 83, 2025. DOI: https://doi.org/https://doi.org/10.1007/s44443-025-00102-6.
  28. Y. Sun, Y. Jin, X. Chen, Y. Xu, X. Yan, Z. L., “Unsupervised detail and color restorer for Retinex-based low-light image enhancement,” Engineering Applications of Artificial Intelligence, vol. 153, pp. 110867, 2025. DOI: https://doi.org/https://doi.org/10.1016/j.engappai.2025.110867.
  29. J. Chen, Z. Xiao, X. Qin, D. L., “Retinex-Based Low-Light Image Enhancement via Spatial-Channel Redundancy Compression and Joint Attention,” Electronics, vol. 14, no. 11, pp. 2212, 2025. DOI: https://doi.org/https://doi.org/10.3390/electronics14112212.
  30. S. Jiang, Y. Shi, Y. Zhang, Y. Z., “An Improved Retinex-Based Approach Based on Attention Mechanisms for Low-Light Image Enhancement,” Electronics, vol. 13, no. 18, pp. 3645, 2024. DOI: https://doi.org/https://doi.org/10.3390/electronics13183645.
  31. X. Liang, X. Chen, K. Ren, X. Miao, Z. Chen, Y. J., “Low-light image enhancement via adaptive frequency decomposition network,” Scientific Reports, vol. 13, no. 1, pp. 14107, 2023. DOI: https://doi.org/https://doi.org/10.1038/s41598-023-40899-8.
  32. D. Liang, Y. Gao, L. Li, Z. Xu, S.-J. Huang, S. C., “Aesthetics-Guided Low-Light Enhancement,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 7, pp. 5866–5883, 2025. DOI: https://doi.org/https://doi.org/10.1109/TPAMI.2025.3554639.
  33. B. Chen, L. Zhu, H. Zhu, W. Yang, L. Song, S. W., “Gap-Closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement,” IEEE Transactions on Multimedia, vol. 26, pp. 3430–3443, 2024. DOI: https://doi.org/https://doi.org/10.1109/TMM.2023.3312851.
  34. Ding, X., and Hu, R., “Learning to see faces in the dark,” 2020 IEEE International Conference on Multimedia and Expo (ICME), 2020, pp. 33.
  35. Wang, W., Yang, W., and Liu, J., “Hla-face: Joint high-low adaptation for low light face detection,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 16195–16204.
  36. Grgic, M., Shan, S., Lukac, R., Wechsler, H., and Bartlett, M. S., “Facial Image Processing and Analysis,” Int J Patt Recog & Artif Intell, vol. 23, no. 3, pp. 355–358, 2009.
  37. Ananthi, G., Balaji, T., Pugalenthi, M., and Rajkumar, M., “Low Light Face Detection System,” Recent Advancements in Multimedia Data Processing and Security: Issues, Challenges, and Techniques, 2023.
  38. S. Munaf, A. Bharathi, A. N. J., “FPGA-based low-light image enhancement using Retinex algorithm and coarse-grained reconfigurable architecture,” vol. 14, no. 1, pp. 28770, 2024. DOI: https://doi.org/https://doi.org/10.1038/s41598-024-80339-9.
  39. G. Wenjuan, C. Ding, J. Wei, Y. Yin, X. L., “Low-light image enhancement based on the fusion of Bilateral filter MSR and AutoMSRCR,” Optics and Precision Engineering, vol. 31, no. 24, pp. 3606–3617, 2023. DOI: https://doi.org/https://doi.org/10.37188/OPE.20233124.3606.
  40. J. Wang, S. Huang, Z. Huo, S. Zhao, Y. Q., “Bilateral enhancement network with signal-to-noise ratio fusion for lightweight generalizable low-light image enhancement,” Scientific Reports, vol. 14, no. 1, pp. 29832, 2024. DOI: https://doi.org/https://doi.org/10.1038/s41598-024-81706-2.
  41. A. Mittal, R. Soundararajan, A. C. B., “Making a ‘Completely Blind’ Image Quality Analyzer,” IEEE Signal Processing Letters, vol. 20, no. 3, pp. 209–212, 2013. DOI: https://doi.org/https://doi.org/10.1109/LSP.2012.2227726.
  42. Mittal, A. K. Moorthy, A. C. B., “No-Reference Image Quality Assessment in the Spatial Domain,” IEEE Transactions on Image Processing, vol. 21, no. 12, pp. 4695–4708, 2012. DOI: https://doi.org/https://doi.org/10.1109/TIP.2012.2214050.