An Efficient Face Recognition System Based on Edge Processing Using GPUs
Main Article Content
Abstract
In this work, an efficient and accurate face recognition system based on edge processing using GPUs was completely developed. A complete pipeline that contains a sequence of processing steps, including pre-processing, face feature extraction, and matching, is proposed. For processing steps, lightweight deep neural models were developed and optimized so that they could be computationally accelerated on an embedded hardware of Nvidia’s Jetson Nano. Besides the core processing pipeline, a database, as well as a user application server were also developed to fully meet the requirements of readily commercialized applications. The experimental evaluation results show that our system has a very high accuracy based on the BLUFR benchmark, with a precision of 98.642%. Also, the system is very computationally efficient, as the computing time to recognize an ID in a dataset of 1171IDs with 10141 images on the Jetson Nano is only 165ms. For the critical case, the system can process 4 camera streams and simultaneously recognize a maximum of 40 IDs within a computing time of 458ms for each ID. With its high-speed and accuracy characteristics, the developed system has a high potential for practical applications.
Keywords
Face recognition, deep learning, GPUs, edge processing.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
[1] Wang, Mei, and Weihong Deng, Deep face recognition: A survey. Neurocomputing, 429, 2021, pp. 215-244. https://doi.org/10.1016/j.neucom.2020.10.081
[2] Nguyen-Xuan H, Hoang-Nhu D, Nguyen-Duy A, and Dang-Minh T, A New Method for IP camera based face anti-spoofing systems, in Proc. Intelligent Systems and Networks: Selected Articles from ICISN 2022, Vietnam (pp. 445-454). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-19-3394-3_48
[3] Nguyen-Xuan H, Hoang-Nhu D, and Dang-Minh T, An evaluation of the multi-probe locality sensitive hashing for large-scale face feature matching. In Proc. Intelligent Systems and Networks: Selected Articles from ICISN 2022, Vietnam (pp. 445-454). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-19-3394-3_51
[4] Dong HN, Ha NX, Tuan DM, A new approach for large-scale face-feature matching based on LSH and FPGA for edge processing. in Proc. Intelligent Systems and Networks ICISN2021: Lecture Notes in Networks and Systems, vol 243. Springer, Singapore. https://doi.org/10.1007/978-981-16-2094-2_42
[5] Cheng KT, Wang YC, Using mobile GPU for generalpurpose computing-a case study of face recognition on smartphones, in Proc. VLSI-DAT, Apr. 25, 2011, pp. 1-4.
[6] Aleksandrova O, Bashkov Y, Face recognition systems based on Neural Compute Stick 2, CPU, GPU comparison, presented at the 2nd Int. Conf. on Advanced Trends in Information Theory, Nov. 25, 2020, pp. 104-107. https://doi.org/10.1109/ATIT50783.2020.9349313
[7] Saypadith S, Aramvith S, Real-time multiple face recognition using deep learning on embedded GPU system, in Proc. APSIPA ASC, Nov. 12, 2018, pp. 1318-1324. https://doi.org/10.23919/APSIPA.2018.8659751
[8] Sati V., Sánchez S. M., Shoeibi N., Arora A., Corchado J. M., Face detection and recognition, face emotion recognition through Nivida Jetson Nano, ISAml, 2021, pp. 177-185. https://doi.org/10.1007/978-3-030-58356-9_18
[9] Xie, Y., Ding, L., Zhou, A. and Chen, G., An optimized face recognition for edge computing, presented at the 13th Int. Conf. on ASIC, Oct, 2019, pp. 1-4. https://doi.org/10.1109/ASICON47005.2019.8983596
[10] GStreamer Plugin Overview - DeepStream 6.2 Release Documentation. [Online] Available: docs.nvidia.com/metropolis/deepstream/devguide/text/DS_plugin_Intro.html. [11] Nvidia DeepStream SDK. Nvidia Developer, 3 Feb. 2023, [Online] Available: developer.nvidia.com/deepstream-sdk.
[12] Wu, K., Zhang, J., Peng, H., Liu, M., Xiao, B., Fu, J. and Yuan, L., Tinyvit: Fast pretraining distillation for small vision transformers, in Proc. ECCV, Tel Aviv, Israel, October 23-27, 2022, Part XXI, pp. 68-85. https://doi.org/10.1007/978-3-031-19803-8_5
[13] Deng, J., Guo, J., Ververas, E., Kotsia, I. and Zafeiriou, S., Retinaface: Single-shot multi-level face localisation in the wild, in Proc. CVPR, Seattle, WA, USA, 2020, pp. 5202-5211. https://doi.org/10.1109/CVPR42600.2020.00525
[14] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L. C., Mobilenetv2: Inverted residuals and linear bottlenecks, in Proc. CVPR, Salt Lake City, UT, USA, 2018, pp. 4510-4520. https://doi.org/10.1109/CVPR.2018.00474
[15] Guo, Y., Zhang, L., Hu, Y., He, X. and Gao, J., Ms-celeb-1m: A dataset and benchmark for large-scale face recognition, in Proc. ECCV, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, pp. 87-102. https://doi.org/10.1007/978-3-319-46487-9_6
[16] Nvidia Jetson Nano Developer Kit. Nvidia Developer, 28 Sept. 2022, [Online] Available: developer.nvidia.com/embedded/jetson-nanodeveloper-kit. [17] Liao, S., Lei, Z., Yi, D. and Li, S. Z., A benchmark study of large-scale unconstrained face recognition, presented at Int. Conf. on biometrics, September, 2014, pp. 1-8. https://doi.org/10.1109/BTAS.2014.6996301
[18] Weisstein, Eric W. Affine Transformation. From MathWorld - A Wolfram Web Resource. [Online] Available: https://mathworld.wolfram.com/AffineTransformatio n.html
[2] Nguyen-Xuan H, Hoang-Nhu D, Nguyen-Duy A, and Dang-Minh T, A New Method for IP camera based face anti-spoofing systems, in Proc. Intelligent Systems and Networks: Selected Articles from ICISN 2022, Vietnam (pp. 445-454). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-19-3394-3_48
[3] Nguyen-Xuan H, Hoang-Nhu D, and Dang-Minh T, An evaluation of the multi-probe locality sensitive hashing for large-scale face feature matching. In Proc. Intelligent Systems and Networks: Selected Articles from ICISN 2022, Vietnam (pp. 445-454). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-19-3394-3_51
[4] Dong HN, Ha NX, Tuan DM, A new approach for large-scale face-feature matching based on LSH and FPGA for edge processing. in Proc. Intelligent Systems and Networks ICISN2021: Lecture Notes in Networks and Systems, vol 243. Springer, Singapore. https://doi.org/10.1007/978-981-16-2094-2_42
[5] Cheng KT, Wang YC, Using mobile GPU for generalpurpose computing-a case study of face recognition on smartphones, in Proc. VLSI-DAT, Apr. 25, 2011, pp. 1-4.
[6] Aleksandrova O, Bashkov Y, Face recognition systems based on Neural Compute Stick 2, CPU, GPU comparison, presented at the 2nd Int. Conf. on Advanced Trends in Information Theory, Nov. 25, 2020, pp. 104-107. https://doi.org/10.1109/ATIT50783.2020.9349313
[7] Saypadith S, Aramvith S, Real-time multiple face recognition using deep learning on embedded GPU system, in Proc. APSIPA ASC, Nov. 12, 2018, pp. 1318-1324. https://doi.org/10.23919/APSIPA.2018.8659751
[8] Sati V., Sánchez S. M., Shoeibi N., Arora A., Corchado J. M., Face detection and recognition, face emotion recognition through Nivida Jetson Nano, ISAml, 2021, pp. 177-185. https://doi.org/10.1007/978-3-030-58356-9_18
[9] Xie, Y., Ding, L., Zhou, A. and Chen, G., An optimized face recognition for edge computing, presented at the 13th Int. Conf. on ASIC, Oct, 2019, pp. 1-4. https://doi.org/10.1109/ASICON47005.2019.8983596
[10] GStreamer Plugin Overview - DeepStream 6.2 Release Documentation. [Online] Available: docs.nvidia.com/metropolis/deepstream/devguide/text/DS_plugin_Intro.html. [11] Nvidia DeepStream SDK. Nvidia Developer, 3 Feb. 2023, [Online] Available: developer.nvidia.com/deepstream-sdk.
[12] Wu, K., Zhang, J., Peng, H., Liu, M., Xiao, B., Fu, J. and Yuan, L., Tinyvit: Fast pretraining distillation for small vision transformers, in Proc. ECCV, Tel Aviv, Israel, October 23-27, 2022, Part XXI, pp. 68-85. https://doi.org/10.1007/978-3-031-19803-8_5
[13] Deng, J., Guo, J., Ververas, E., Kotsia, I. and Zafeiriou, S., Retinaface: Single-shot multi-level face localisation in the wild, in Proc. CVPR, Seattle, WA, USA, 2020, pp. 5202-5211. https://doi.org/10.1109/CVPR42600.2020.00525
[14] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L. C., Mobilenetv2: Inverted residuals and linear bottlenecks, in Proc. CVPR, Salt Lake City, UT, USA, 2018, pp. 4510-4520. https://doi.org/10.1109/CVPR.2018.00474
[15] Guo, Y., Zhang, L., Hu, Y., He, X. and Gao, J., Ms-celeb-1m: A dataset and benchmark for large-scale face recognition, in Proc. ECCV, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, pp. 87-102. https://doi.org/10.1007/978-3-319-46487-9_6
[16] Nvidia Jetson Nano Developer Kit. Nvidia Developer, 28 Sept. 2022, [Online] Available: developer.nvidia.com/embedded/jetson-nanodeveloper-kit. [17] Liao, S., Lei, Z., Yi, D. and Li, S. Z., A benchmark study of large-scale unconstrained face recognition, presented at Int. Conf. on biometrics, September, 2014, pp. 1-8. https://doi.org/10.1109/BTAS.2014.6996301
[18] Weisstein, Eric W. Affine Transformation. From MathWorld - A Wolfram Web Resource. [Online] Available: https://mathworld.wolfram.com/AffineTransformatio n.html