Performance Evaluation of YOLOv8 and RetinaFace for Real-Time Face Detection on Edge Devices
DOI:
https://doi.org/10.68307/18xagk59Keywords:
YOLOv8, RetinaFace, Face Detection, Edge Computing, Raspberry Pi 4, RealTime Processing, Deep Learning, Computer Vision, Lightweight Neural Networks, Performance EvaluationAbstract
The demand for efficient and accurate face detection in real-time applications has increased significantly with the rise of Internet of Things (IoT) and embedded vision systems. Deploying deep learning models on low-power edge devices such as the Raspberry Pi 4 presents challenges related to limited memory, computation capability, and energy consumption. This study evaluates the performance of two modern deep learning architectures—YOLOv8 and RetinaFace—for real-time face detection on the Raspberry Pi 4 platform. Both models were tested using the WIDER FACE and FDDB datasets under identical hardware and software configurations. Performance metrics including detection accuracy, latency, frames per second (FPS), and power usage were analyzed to assess suitability for edge deployment. Experimental results indicate that YOLOv8 achieves higher inference speed with acceptable accuracy, whereas RetinaFace provides superior detection precision at the cost of increased latency. The comparative analysis highlights the trade-off between real-time responsiveness and detection accuracy, providing insights into selecting an optimal model for resource-constrained environments. The findings can guide researchers and developers in implementing lightweight, efficient, and reliable face detection systems for next-generation edge-AI applications.
References
[1] J. Deng, J. Guo, E. Ververas, I. Kotsia, and S. Zafeiriou, “RetinaFace: Single Shot Multi Level Face Localisation in the Wild,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2020, pp. 5203–5212.
[2] V. Bazarevsky, Y. Kartynnik, A. Vakunov, K. Raveendran, and M. Grundmann, “BlazeFace: Sub millisecond Neural Face Detection on Mobile GPUs,” arXiv:1907.05047, 2019.
[3] S. Chen, Y. Liu, X. Gao, and Z. Han, “MobileFaceNets: Efficient CNNs for Accurate Real Time Face Verification on Mobile Devices,” in Chinese Conf. Biometric Recognition, 2018, pp. 428–438, doi: 10.1007/978-3-319-97909-0_46.
[4] S. Yang, P. Luo, C. C. Loy, and X. Tang, “WIDER FACE: A Face Detection Benchmark,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 5525–5533.
[5] V. Jain and E. Learned Miller, “FDDB: A Benchmark for Face Detection in Unconstrained Settings,” Univ. Massachusetts Amherst, Tech. Rep. UM-CS-2010-009, 2010.
[6] S. Zhang, X. Zhu, Z. Lei, H. Shi, X. Wang, and S. Z. Li, “S3FD: Single Shot Scale Invariant Face Detector,” in Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 192–201.
[7] X. Tang, D. K. Du, Z. He, and J. Liu, “PyramidBox: A Context Assisted Single Shot Face Detector,” in Proc. Eur. Conf. Comput. Vis., 2018, pp. 797–813.
[8] S. Zhang, X. Zhu, Z. Lei, H. Shi, X. Wang, and S. Z. Li, “FaceBoxes: A CPU Real Time Face Detector with High Accuracy,” in 2017 IEEE Int. Joint Conf. Biometrics, 2017, pp. 1–9, doi: 10.1109/BTAS.2017.8272675.
[9] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified Real Time Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 779–788.
[10] A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv:2004.10934, 2020.
[11] Ultralytics, “YOLOv8 Documentation,” 2023. [Online]. Available: https://docs.ultralytics.com/models/yolov8/. Accessed: Sep. 26, 2026.
[12] NVIDIA, “TensorRT Documentation.” [Online]. Available: https://docs.nvidia.com/deeplearning/tensorrt/. Accessed: Sep. 26, 2026.
[13] H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, “Pruning Filters for Efficient ConvNets,” in Int. Conf. Learn. Representations, 2017.
[14] B. Jacob et al., “Quantization and Training of Neural Networks for Efficient Integer Arithmetic Only Inference,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 2704–2713.
[15] G. Hinton, O. Vinyals, and J. Dean, “Distilling the Knowledge in a Neural Network,” arXiv:1503.02531, 2015.
[16] M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” in Proc. 36th Int. Conf. Mach. Learn., vol. 97, 2019, pp. 6105–6114.
[17] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 4510–4520.
[18] S. Zafeiriou, C. Zhang, and Z. Zhang, “A Survey on Face Detection in the Wild: Past, Present and Future,” Comput. Vis. Image Underst., vol. 138, pp. 1–24, 2015, doi: 10.1016/j.cviu.2015.03.015.
[19] C. Banbury et al., “MLPerf Tiny Benchmark,” in Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks, vol. 1, 2021.
[20] Raspberry Pi Ltd., “Raspberry Pi 4 Model B Specifications.” [Online]. Available: https://www.raspberrypi.com/products/raspberry-pi-4-model-b/. Accessed: Sep. 26, 2026.
[21] M. K. Bagwani and G. K. Shrivastava, “Comparative analysis of microservices architectures: Evaluating performance, scalability, and maintenance,” *International Journal on Advances in Engineering Technology and Science*, vol. 5, no. 32, p. 33, 2023.
[22] M. K. Bagwani, “Deploying a web application on AWS Amplify: A comprehensive guide,” *International Journal of Progressive Research in Engineering Management and Science*, vol. 4, no. 8, pp. 538–544, 2024, doi: 10.58257/IJPREMS35750.
[23] M. K. Bagwani, V. K. Tiwari, and A. Jain, “Implementing GrapesJS in educational platforms for web development training on AWS,” *International Journal of Scientific Research in Multidisciplinary Studies*, vol. 10, no. 8, pp. 1–8, 2024.
[24] M. K. Bagwani, V. K. Tiwari, A. Gangwar, and K. Vishwakarma, “Real-time signature-based detection and prevention of DDoS attacks in cloud environments,” *International Journal of Science and Research Archive*, vol. 12, no. 2, pp. 2929–2935, 2024, doi: 10.30574/ijsra.2024.12.2.1608.
[25] M. K. Bagwani, V. K. Tiwari, and A. Jain, “Optimizing face detection performance with cloud machine learning services,” *Journal of Engineering and Technology Management*, vol. 73, pp. 1167–1180, 2024, doi: 20.14118/v73.2024.102213.
[26] M. K. Bagwani, V. K. Tiwari, and A. Jain, “Preventing malware spread through QR codes: A detection and analysis approach,” *Journal of Engineering and Technology Management*, vol. 73, pp. 1260–1268, 2024.
[27] M. K. Bagwani, S. Dwivedi, V. Kumar, P. Koshti, and S. Jain, “Transmitting malware through QR codes: Risk analysis and a hybrid detection method,” *International Journal for Multidisciplinary Research*, vol. 8, no. 3, pp. 1–25, 2026.
[28] M. K. Bagwani and G. Gupta, “Random forest over semantic PDF object graphs for robust malware detection,” *International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies (IJAICET)*, vol. 1, no. 1, pp. 1–5, 2026.
[29] G. Sharma and G. Shrivastava, “Crop disease prediction using deep learning techniques—A review,” SSRG International Journal of Computer Science and Engineering, vol. 9, no. 4, pp. 23–28, 2022.
[30] M. K. Bagwani and G. K. Shrivastava, “Comparative analysis of microservices architectures: Evaluating performance, scalability, and maintenance,” Development, vol. 5, no. 32, p. 33, 2023.
[31] S. Gupta, M. Singh, and S. Srivastava, “Wireless sensor network: A survey,” in Proc. Conference Paper, Oct. 2018.
[32] M. K. Bagwani and G. K. Shrivastava, “Performance comparison of REST API and GraphQL in a microservices architecture,” in Proc. International Conference on Data Science, Artificial Intelligence and Machine Learning, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ms. Divya Thakre, Dr. khushbu Rai
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies (IJAICET) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Under this license, users are free to share, copy, redistribute, adapt, and build upon the published material for any purpose, including commercial use, provided appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.
Authors retain copyright of their work while granting IJAICET the right to publish, archive, distribute, and index the article. The journal supports the free exchange of scientific knowledge through open access publishing and encourages the widest possible dissemination of research.
