Detecting Human Faces in Three Different Environmental Conditions using YOLOv4

Article Sidebar

PDF
Published: Apr 23, 2024
Keywords:
Detecting human faces YOLOv4 Different environmental Confusion matrix

Main Article Content

Pisanu Kumeechai
Department of Engineering, Education Branch, Royal Thai Naval Academy, Samut Prakan 10270

Abstract

This research focuses on detecting human faces using the YOLOv4 model and compares it with other algorithms used in face detection studies. The dataset consists of a large number of images taken in three significantly different environmental conditions: indoors with low light, indoors with sufficient light, and outdoors during normal daylight hours. The performance of each algorithm in detecting human faces is measured and compared with four other algorithms: Viola-Jones Face Detection Algorithm, DeepFace, FaceNet, and MTCNN. The results of the experiment show that the YOLOv4 model outperforms the other algorithms in all three environmental conditions. According to confusion matrix evolution, the average precision for detecting human faces using the YOLOv4 model is 0.96, with a recall of 0.93 and an f1-score of 0.94. Therefore, the YOLOv4 algorithm is the most effective algorithm for detecting human faces in this study.

Article Details

Issue
Vol.32 No.2 (March-April 2024)
Section
Engineering and Architecture

References

Deng, D., Guo, J., & Yuxiang, Z. (2020). RetinaFace: Single-stage Dense Face Localisation in the Wild. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, 5203-5212.

Qin, Z., Zhang, Y., Huang, K., & Zhao, D. (2020). Towards Mask Face Detection with A Convolutional Neural Network. Applied Sciences, 10(17), 5945.

Arumugam, P., & Natarajan, N. (2017). A Survey of Face Detection, Extraction and Recognition. International Journal of Computer Applications, 163(7), 1-6.

Ranjan, R., Sankaranarayanan, S., & Castillo, C. D. (2020). Deep Learning-based Face Detection: A Comprehensive Survey. ACM Computing Surveys (CSUR), 53(6), 1-36.

Le, N. N. H., & Bui, T. D. (2021). Face Detection and Recognition using Deep Learning: A Survey. Journal of Ambient Intelligence and Humanized Computing, 12(2), 1735-1757.

Sarfraz, M. S., & Alahakoon, R. (2018). Face Detection and Recognition Techniques: A Survey. Journal of King Saud University-Computer and Information Sciences, 30(4), 428-444.

Ahmed, S. M., Abd El-Latif, S. M., Aly, S. S., & ElAlfy, A. S. (2020). A Comprehensive Survey of Face Recognition Techniques. IEEE Access, 8, 158557-158576.

Goyal, P., Bhatia, K., & Singh, R. (2017). Face Recognition Techniques: A Comprehensive Survey. International Journal of Computer Applications, 160(1), 18-25.

Zhou, Y., Liao, S., & Li, S. Z. (2018). Recent progress in facial landmark detection. arXiv preprint arXiv:1806.01893.

Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1701-1708).

Zhang, Z., Luo, P., Loy, C. C., & Tang, X. (2015). Facial landmark detection by deep multi-task learning. In European conference on computer vision (pp. 94-108).

Xie, S., Girshick, R., Dollár, P., Tu, Z., & He, K. (2016). Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1492-1500).

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). SSD: Single shot multibox detector. In European conference on computer vision (pp. 21-37).

Wu, X., He, R., Sun, Z., & Tan, T. (2018). A light CNN for deep face representation with noisy labels. IEEE Transactions on Information Forensics and Security, 13(11), 2884-2896.

Dang, H., & Chan, C. S. (2019). Unconstrained face detection using deep learning and multi-task learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 0-0).

Li, Y., Li, F., Li, S., Li, X., & Chen, J. (2020). A novel attention-based deep convolutional neural network for facial landmark detection. Cognitive Computation, 12(3), 449-459.

Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934.

Wang, X., Liu, D., & Yu, X. (2021). Adaptive object detection for human faces using YOLOv4. Multimedia Tools and Applications, 80(16), 24807-24822.

Kumar, M., Singh, M., Verma, A. K., & Chandra, S. (2021). Performance evaluation of YOLOv4 and RetinaNet for face detection. Journal of Ambient Intelligence and Humanized Computing, 12(10), 11503-11512.

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).

Maghraby M.AbdallaO.Enany,Hybrid Face Detection System using Combination of Viola - Jones Method and Skin Detection, International Journal of Computer Applications (0975 – 8887) Volume 71– No.6, May 2013

Li Zhihua, Zhang Jianyu & Wei Zhongcheng. (2022). Design on face recognition system based on MTCNN and Facenet. Modern Electronic Technology (04), 139-143.

Zhang Ying. (2022). Study on improved face recognition algorithm based on Facenet. Electronic Technology (03), 25-27.

Schroff, F., Kalenichenko, D. & Philbin, J. (2015). FaceNet: A Unified Embedding for Face Recognition and Clustering. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Wang, J., & Wang, L. (2013). Face Recognition: A Survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 43(3), 401-422.