Optimalisasi Pengenalan Wajah Pada Kondisi Low Light Menggunakan YOLOv5 Face Dan CLAHE

Rayhan Ferdiansyah; Erna Daniati; Aidina  Ristyawan

doi:10.47065/bit.v7i2.2784

Rayhan Ferdiansyah Universitas Nusantara PGRI Kediri, Indonesia
Erna Daniati * Universitas Nusantara PGRI Kediri, Indonesia
Aidina Ristyawan Universitas Nusantara PGRI Kediri, Indonesia

DOI: https://doi.org/10.47065/bit.v7i2.2784

Keywords: Pengenalan Wajah; Cahaya Rendah; CLAHE; YOLOv5; FaceNet

Abstract

Degradation of illumination intensity in low light environments is a major issue that reduces the accuracy of deep learning based face detection and recognition systems. This study aims to optimize the performance of the biometric processing pipeline under extreme low light conditions without retraining the model. The novelty of this research lies in the design of a retrainless integration between the hybrid preprocessing of CLAHE and Bilateral Filter on the luminance channel of the LAB color space with the integrated processing pipeline of YOLOv5-Face and FaceNet. Mass testing was conducted using pair-based evaluation on 3,000 face pairs from the VGGFace2 benchmark dataset, simulated in a controlled manner using a gamma exponent value (y = 0,5). Experimental results show that the preprocessing stage successfully restored the YOLOv5-Face Detection Rate from 88.7% to 89.8%. Meanwhile, in the identity verification stage, the FaceNet model recorded an increase in class separability, achieving the highest Area Under the Curve (AUC-ROC) value of 0.927 (classified as excellent), a global accuracy of 89.3%, and the ability to maintain the stability of the Cosine Distance Gap at an index of 0.6005. This characteristic proves the robustness of the feature vector geometry in separating boundaries between identities without overlapping. The implementation of the system into a Streamlit web application confirms that this traditional contrast restoration method remains relevant, efficient, and reliable for securing biometric verification under low-light conditions.

References

H. Du, H. Shi, D. Zeng, X.-P. Zhang, and T. Mei, “The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances,” ACM Comput. Surv., vol. 54, no. 10s, Sep. 2022, doi: 10.1145/3507902.

C. Li et al., “Low-Light Image and Video Enhancement Using Deep Learning: A Survey,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 12, pp. 9396–9416, 2022, doi: 10.1109/TPAMI.2021.3126387.

G. Jocher et al., “ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation ,” Nov. 2022, Zenodo. doi: 10.5281/zenodo.7347926.

J. Deng, J. Guo, J. Yang, N. Xue, I. Kotsia, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 10, pp. 5962–5979, 2022, doi: 10.1109/TPAMI.2021.3087709.

S. U. A. Shovo, Md. G. R. Abir, Md. M. Kabir, and M. F. Mridha, “Advancing low-light object detection with you only look once models: An empirical study and performance evaluation,” Cognitive Computation and Systems, vol. 6, no. 4, pp. 119–134, Dec. 2024, doi: https://doi.org/10.1049/ccs2.12114.

D. Peng, W. Ding, and T. Zhen, “A novel low light object detection method based on the YOLOv5 fusion feature enhancement,” Sci. Rep., vol. 14, no. 1, p. 4486, 2024, doi: 10.1038/s41598-024-54428-8.

L. N. Soni and A. A. Waoo, “Face Detection Under Low-Light and Low-Resolution Conditions Using Contrast-Limited Adaptive Histogram Equalization and a Modified Convolutional Neural Network,” 2025. [Online]. Available: https://www.jneonatalsurg.com

Y. Fan et al., “Low-FaceNet: Face Recognition-Driven Low-Light Image Enhancement,” IEEE Trans. Instrum. Meas., vol. 73, pp. 1–13, 2024, doi: 10.1109/TIM.2024.3372230.

Q. Lu and P. Gan, “Low-Light Face Recognition and Identity Verification Based on Image Enhancement,” Traitement du Signal, vol. 39, no. 2, pp. 513–519, Apr. 2022, doi: 10.18280/ts.390213.

I. and P. M. and K. B. De Shreya and Pandey, “Face Recognition Using Image Enhancement in Low Light Conditions,” in VLSI, Microwave and Wireless Technologies, S. Kumar Dharmendra and Kumar, Ed., Singapore: Springer Nature Singapore, 2026, pp. 363–369.

K. C. Paul and S. Aslan, “An Improved Real-Time Face Recognition System at Low Resolution Based on Local Binary Pattern Histogram Algorithm and CLAHE,” Optics and Photonics Journal, vol. 11, no. 04, pp. 63–78, 2021, doi: 10.4236/opj.2021.114005.

F. Martínez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 8, pp. 3048–3061, 2021, doi: 10.1109/TKDE.2019.2962680.

M. Wang and W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, Mar. 2021, doi: 10.1016/J.NEUCOM.2020.10.081.

Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman, “VGGFace2: A dataset for recognising faces across pose and age,” May 2018, [Online]. Available: http://arxiv.org/abs/1710.08092

V. S., J. D. B. C., S. P., and S. K., “RETRACTED ARTICLE: Image Enhancement and Implementation of CLAHE Algorithm and Bilinear Interpolation,” Cybern. Syst., vol. 0, no. 0, pp. 1–13, 2022, doi: 10.1080/01969722.2022.2147128.

D. Qi, W. Tan, Q. Yao, and J. Liu, “YOLO5Face: Why Reinventing a Face Detector,” Jan. 2022, [Online]. Available: http://arxiv.org/abs/2105.12931

R. Goel, I. Mehmood, and H. Ugail, “A Study of Deep Learning-Based Face Recognition Models for Sibling Identification,” Sensors, vol. 21, no. 15, 2021, doi: 10.3390/s21155068.

L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, Dec. 2021, doi: 10.1186/s40537-021-00444-8.

I. Lashkov, R. Yuan, and G. Zhang, “Edge-Computing-Facilitated Nighttime Vehicle Detection Investigations With CLAHE-Enhanced Images,” Trans. Intell. Transport. Sys., vol. 24, no. 11, pp. 13370–13383, Nov. 2023, doi: 10.1109/TITS.2023.3255202.