Enhancing Face Detection Performance under Various Illumination Conditions using YOLO and Haar Cascade with Canny Edge Detection

Authors

  • Pisanu Kumeechai Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Napadach Attachareanwong Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Jitti Sampattakul Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Teeraphat Sarawan Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Krittanai Singphueak Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Saranphat Maliphrom Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Witchakorn Chaiorawan Department of Engineering, Education Branch, Royal Thai Naval Academy
  • Sueppong Wattanaprukchat Department of Engineering, Education Branch, Royal Thai Naval Academy

Keywords:

face detection, YOLO, Haar Cascade, Canny Edge Detection, varying illumination conditions

Abstract

The primary challenge in face detection is performance instability under varying illumination conditions, particularly in low-light environments. This research aims to enhance face detection accuracy under high, medium, and low lighting conditions by integrating YOLO, Haar Cascade, and Canny Edge Detection. Canny Edge Detection is employed as a pre-processing step to emphasize facial contours and mitigate illumination effects prior to model input. Performance evaluation was conducted using standard metrics, including Accuracy, Precision, and Recall, on a dataset of 1,500 images. Experimental results indicate that the integration of YOLO with Canny Edge Detection (YOLO + Canny) significantly outperformed the other methods, achieving the highest average Accuracy of (92.0%) under medium lighting conditions, while maintaining high performance under high light (91.0%) and low light (87.2%). Furthermore, the YOLO + Canny approach demonstrated the lowest processing time, at less than 0.2 seconds per image. In conclusion, the integration of YOLO and Canny Edge Detection provides high robustness, speed, and accuracy for face detection across varying illumination conditions, demonstrating strong potential for real-world applications.

References

Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. https://doi.org/10.48550/arXiv.2004.10934

Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), 679–698. https://doi.org/10.1109/TPAMI.1986.4767851

Hong, M., Cheng, S., Huang, H., Fan, H., & Liu, S. (2024). You only look around: Learning illumination-invariant feature for low-light object detection. arXiv:2410.18398. https://doi.org/10.48550/arXiv.2410.18398

Jobson, D. J., Rahman, Z., & Woodell, G. A. (1997). A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Transactions on Image Processing, 6, 965-976. https://doi.org/10.1109/83.597272

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386

Li, Y., & Deng, W. (2020). Deep face recognition: A survey. Neurocomputing, 429, 215–244. https://doi.org/10.1016/j.neucom.2020.01.085

Lienhart, R., & Maydt, J. (2002). An extended set of Haar-like features for rapid object detection. In B. Mercer & L. Cotton (Eds.), Proceedings of the 2002 International Conference on Image Processing (ICIP) (pp. 900–903). IEEE. https://doi.org/10.1109/ICIP.2002.1038171

Liu, Y., Li, S., Zhou, L., Liu, H., & Li, Z. (2025). Dark-YOLO: A low-light object detection algorithm integrating multiple attention mechanisms. Applied Sciences, 15(9), 5170. https://doi.org/10.3390/app15095170

Maini, R., & Aggarwal, H. (2009). Study and comparison of various image edge detection techniques. International Journal of Image Processing, 3(1), 1–11. https://www.cscjournals.org/manuscript/Journals/IJIP/Volume3/Issue1/IJIP-15.pdf

Mittal, P. (2024). A comprehensive survey of deep learning-based lightweight object detection models for edge devices. Artificial Intelligence Review, 57, 242. https://doi.org/10.1007/s10462-024-10877-1

Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., Romeny, B. H., Zimmerman, J. B., & Zuiderveld, K. (1987). Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing, 39(3), 355–368. https://doi.org/10.1016/S0734-189X(87)80186-X

Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv:2010.16061. https://doi.org/10.48550/arXiv.2010.16061

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 779–788). IEEE.

Sun, R., Lei, T., Chen, Q., Wang, Z., Du, X., Zhao, W., & Nandi, A. K. (2022). Survey of image edge detection. Frontiers in Signal Processing, 2, 826967. https://doi.org/10.3389/frsip.2022.826967

Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 1, pp. I–I). IEEE.

Yisihak, H. M., & Li, L. (2024). Advanced face detection with YOLOv8: Implementation and integration into AI modules. Open Access Library Journal, 11(11), e12474. https://doi.org/10.4236/oalib.1112474

Zareiforoush, H., Minaei, S., Alizadeh, M. R., & Banakar, A. (2016). An intelligent system design for classification of milled rice grains using metaheuristic methods. Measurement, 90, 350–361. https://doi.org/10.1016/j.measurement.2016.04.091

Zhang, C., & Zhang, Z. (2010). A survey of recent advances in face detection [Technical Report MSR-TR-2010-66]. Microsoft Research.

Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499-1503. https://doi.org/10.1109/lsp.2016.2603342

Zhou, Z., Cao, Z., & Pi, Y. (2017). A robust face detection method based on skin color and edge detection. Multimedia Tools and Applications, 76(7), 9711–9726. https://doi.org/10.1007/s11042-016-3507-3

Downloads

Published

2026-08-19

How to Cite

Kumeechai, P., Attachareanwong, N., Sampattakul, J., Sarawan, T., Singphueak, K., Maliphrom, S., Chaiorawan, W., & Wattanaprukchat, S. (2026). Enhancing Face Detection Performance under Various Illumination Conditions using YOLO and Haar Cascade with Canny Edge Detection. EAU Heritage Journal Science and Technology (online), 20(2), 80–99. retrieved from https://he01.tci-thaijo.org/index.php/EAUHJSci/article/view/283461

Issue

Section

Research Articles