Empirical Analysis of Deep Learning Models for Real-time Face Detection on Resource-constrained Devices

Bassey Isong; Sedzani Ndouvhada; Otshepeng Kgote

doi:10.25299/itjrd.2025.22402

Authors

Bassey Isong Department of Computer Science, North-West University, South Africa
Sedzani Ndouvhada Department of Computer Science, North-West University, South Africa
Otshepeng Kgote Department of Computer Science, North-West University, South Africa

DOI:

https://doi.org/10.25299/itjrd.2025.22402

Keywords:

Face Detection, YOLOv8, SSD, Faster RCNN, Mobile Devices

Abstract

Face detection (FD) technology enables machines to identify human faces, playing a critical role in mobile device security and user interaction. However, achieving an optimal balance between speed and accuracy in FD algorithms remains a challenge, particularly for real-time applications on resource-limited devices. Factors such as variations in pose, lighting conditions, occlusions, dataset diversity, and hardware constraints often hinder effective deployment. This study presents a comprehensive empirical evaluation of deep learning-based object detection techniques, specifically YOLOv8, SSD, and Faster RCNN, to assess their effectiveness in addressing real-world scalability and performance demands. These models were trained on diverse datasets and evaluated using key performance metrics, including accuracy, precision, recall, and frames per second (FPS). YOLOv8 achieved superior performance, achieving 42.32 FPS with an accuracy of 86%, surpassing two-stage models in real-time processing speed while maintaining comparable accuracy. The findings underscore the importance of dataset quality and diversity in enhancing model performance and positioning YOLOv8 as an effective solution for balancing speed and accuracy on the COCO dataset. The study envisions a future exploration of hybrid models that integrate YOLOv8's efficiency with Faster RCNN's precision to develop more robust FD solutions tailored to real-world challenges.

Downloads

Download data is not yet available.

References

[1] K. Dang and S. Sharma, "Review and comparison of face detection algorithms," in 2017 7th International Conference on Cloud Computing, Data Science & Engineering-Confluence, 2017, pp. 629-633.

[2] B. Kranthikiran and P. Pulicherla, "Face detection and recognition for use in campus surveillance," International Journal of Innovative Technology and Exploring Engineering, vol. 9, pp. 2908-2913, 2020.

[3] N. Zhang, J. Luo, and W. Gao, "Research on face detection technology based on MTCNN," in 2020 International Conference on Computer Network, Electronics and Automation (ICCNEA), 2020, pp. 154-158.

[4] M. Shi and Y. Gao, "Lightweight real-time face detection method based on improved YOLOv4," in 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI), 2021, pp. 273-277.

[5] X. Liu, Y. Zhang, Z. Wang, and J. Yang, "Research on Deep Learning Model and Optimisation Algorithm in Edge Computing," in 2023 5th International Conference on Applied Machine Learning (ICAML), 2023, pp. 242-246.

[6] F. Majeed, F. Z. Khan, M. Nazir, Z. Iqbal, M. Alhaisoni, U. Tariq, et al., "Investigating the efficiency of deep learning based security systems in a real-time environment using YOLOv5," Sustainable Energy Technologies and Assessments, vol. 53, p. 102603, 2022.

[7] M. Wieczorek, J. Siłka, M. Woźniak, S. Garg, and M. M. Hassan, "Lightweight convolutional neural network model for human face detection in risk situations," IEEE Transactions on Industrial Informatics, vol. 18, pp. 4820-4829, 2021.

[8] S. S. Phatak, H. S. Patil, M. W. Arshad, B. Jitkar, S. Patil, and J. Patil, "Advanced face detection using machine learning and AI-based algorithm," in 2022 5th International Conference on Contemporary Computing and Informatics (IC3I), 2022, pp. 1111-1116.

[9] Y. Guo and B. C. Wünsche, "Comparison of face detection algorithms on mobile devices," in 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), 2020, pp. 1-6.

[10] R. Ranjan, A. Bansal, J. Zheng, H. Xu, J. Gleason, B. Lu, et al., "A fast and accurate system for face detection, identification, and verification," IEEE Transactions on Biometrics, Behaviour, and Identity Science, vol. 1, pp. 82-96, 2019.

[11] A. K. Sirivarshitha, K. Sravani, K. S. Priya, and V. Bhavani, "An approach for face detection and face recognition using OpenCV and face recognition libraries in Python," in 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS), 2023, pp. 1274-1278.

[12] S. Reddy, S. Goel, and R. Nijhawan, "Real-time face mask detection using machine learning/deep feature-based classifiers for face mask recognition," in 2021 IEEE Bombay Section Signature Conference (IBSSC), 2021, pp. 1-6.

[13] M. Anand and S. Babu, "Multi-class facial emotion expression identification using DL-based feature extraction with classification models," International Journal of Computational Intelligence Systems, vol. 17, p. 25, 2024.

[14] M. K. Hasan, M. S. Ahsan, S. S. Newaz, and G. M. Lee, "Human face detection techniques: A comprehensive review and future research directions," Electronics, vol. 10, p. 2354, 2021.

[15] Y. Zennayi, S. Benaissa, H. Derrouz, and Z. Guennoun, "Unauthorised access detection system to the equipment in a room based on the person's identification by face recognition," Engineering Applications of Artificial Intelligence, vol. 124, p. 106637, 2023.

[16] S. J. Prince, J. Elder, Y. Hou, M. Sizinstev, and E. Olevskiy, "Towards face recognition at a distance," in 2006 IET Conference on Crime and Security, 2006, pp. 570-575.

[17] A. Figueira and B. Vaz, "Survey on synthetic data generation, evaluation methods and GANs," Mathematics, vol. 10, p. 2733, 2022.

[18] T. He, R. Kong, A. J. Holmes, M. Nguyen, M. R. Sabuncu, S. B. Eickhoff, et al., "Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behaviour and demographics," NeuroImage, vol. 206, p. 116276, 2020.

[19] M. Carranza-García, J. Torres-Mateo, P. Lara-Benítez, and J. García-Gutiérrez, "On the performance of one-stage and two-stage object detectors in autonomous vehicles using camera data," Remote Sensing, vol. 13, p. 89, 2020.

[20] L. Du, R. Zhang, and X. Wang, "Overview of two-stage object detection algorithms," in Journal of Physics: Conference Series, 2020, p. 012033.

[21] M. B. Ullah, "CPU based YOLO: A real time object detection algorithm," in 2020 IEEE Region 10 Symposium (TENSYMP), 2020, pp. 552-555.

[22] R. Rameswari, S. N. Kumar, M. A. Aananth, and C. Deepak, "Automated access control system using face recognition," Materials Today: Proceedings, vol. 45, pp. 1251-1256, 2021.

[23] R. Fatima, R. Sadiq, I. Ullah, S. Manzoor, S. A. Memon, and U. Khan, "Multiple passive-sensor distributed target tracking approach with machine learning feedback," Expert Systems with Applications, vol. 238, p. 122344, 2024.

[24] A. Fernández, R. Usamentiaga, J. L. Carús, and R. Casado, "Driver distraction using visual-based sensors and algorithms," Sensors, vol. 16, p. 1805, 2016.

[25] A. Aldhaheri, F. Alwahedi, M. A. Ferrag, and A. Battah, "Deep learning for cyber threat detection in IoT networks: A review," Internet of Things and cyber-physical systems, vol. 4, pp. 110-128, 2024.

[26] S. Alfattama, P. Kanungo, and S. K. Bisoy, "Face Recognition from Partial Face Data," in 2021 International Conference in Advances in Power, Signal, and Information Technology (APSIT), 2021, pp. 1-5.

[27] B. Amirgaliyev, M. Mussabek, T. Rakhimzhanova, and A. Zhumadillayeva, "A Review of Machine Learning and Deep Learning Methods for Person Detection, Tracking and Identification, and Face Recognition with Applications," Sensors, vol. 25, p. 1410, 2025.

[28] J. Ahmad, S. Akram, A. Jaffar, Z. Ali, S. M. Bhatti, A. Ahmad, et al., "Deep learning empowered breast cancer diagnosis: Advancements in detection and classification," Plos one, vol. 19, p. e0304757, 2024.

[29] Y. Liu, P. Sun, N. Wergeles, and Y. Shang, "A survey and performance evaluation of deep learning methods for small object detection," Expert Systems with Applications, vol. 172, p. 114602, 2021.

[30] Y. Liu, "An improved faster R-CNN for object detection," in 2018 11th International Symposium on Computational Intelligence and Design (ISCID), 2018, pp. 119-123.

[31] K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, "Joint face detection and alignment using multitask cascaded convolutional networks," IEEE Signal Processing Letters, vol. 23, pp. 1499-1503, 2016.

[32] M. Phankokkruad and P. Jaturawat, "An evaluation of technical study and performance for real-time face detection using Web Real-Time Communication," in 2015 International Conference on Computer, Communications, and Control Technology (I4CT), 2015, pp. 162-166.

[33] Z. Liu, Q. Qi, S. Wang, and G. Zhai, "A novel approach to the detection of facial wrinkles: Database, detection algorithm, and evaluation metrics," Computers in Biology and Medicine, vol. 174, p. 108431, 2024.

[34] D. Al-obidi and S. Kacmaz, "Facial Features Recognition Based on Their Shape and Color Using YOLOv8," in 2023 7th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2023, pp. 1-6.

[35] C. Zhang, G. Liu, X. Zhu, and H. Cai, "Face detection algorithm based on improved AdaBoost and new haar features," in 2019 12th International Congress on Image and signal processing, BioMedical Engineering and Informatics (CISP-BMEI), 2019, pp. 1-5.

[36] D. Garg, P. Goel, S. Pandya, A. Ganatra, and K. Kotecha, "A deep learning approach for face detection using YOLO," in 2018 IEEE Punecon, 2018, pp. 1-4.

[37] K. Wang, X. Peng, J. Yang, D. Meng, and Y. Qiao, "Region attention networks for pose and occlusion robust facial expression recognition," IEEE Transactions on Image Processing, vol. 29, pp. 4057-4069, 2020.

[38] X.. Sun, P. Wu, and S. C. Hoi, "Face detection using deep learning: An improved faster RCNN approach," Neurocomputing, vol. 299, pp. 42-50, 2018.

[39] J. Guo, Z. Wang, and S. Zhang, "FESSD: Feature enhancement single shot multibox detector algorithm for remote sensing image target detection," Electronics, vol. 12, p. 946, 2023.

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

[41] R. T. Hasan and A. B. Sallow, "Face detection and recognition using OpenCV," Journal of Soft Computing and Data Mining, vol. 2, pp. 86-97, 2021.

[42] Z.-Q. Zhao, P. Zheng, S.-t. Xu, and X. Wu, "Object detection with deep learning: A review," IEEE Transactions on Neural Networks and learning systems, vol. 30, pp. 3212-3232, 2019.

[43] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, et al., "SSD: Single shot multibox detector," in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, 2016, pp. 21-37.

[44] D. Demetriou, P. Mavromatidis, P. M. Robert, H. Papadopoulos, M. F. Petrou, and D. Nicolaides, "Real-time construction demolition waste detection using state-of-the-art deep learning methods; single–stage vs two-stage detectors," Waste Management, vol. 167, pp. 194-203, 2023.

[45] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 1137-1149, 2016.

[46] R. Padilla, S. L. Netto, and E. A. Da Silva, "A survey on performance metrics for object-detection algorithms," in 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), 2020, pp. 237-242.

[47] E. L. T. Jun, M.-L. Tham, and B.-H. Kwan, "A Comparative Analysis of RT-DETR and YOLOv8 for Urban Zone Aerial Object Detection," in 2024 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), 2024, pp. 340-345.

[48] C. Dewi, D. Manongga, and E. Mailoa, "Deep Learning-Based Face Mask Recognition System with YOLOv8," in 2024 16th International Conference on Computer and Automation Engineering (ICCAE), 2024, pp. 418-422.