Optimising a pretrained CNN for biometric authentication based on facial features in an IoT system
Abstract
Biometric authentication based on facial features has emerged as a secure and user-friendly method for identity verification in Internet of Things (IoT) systems. However, deploying high-accuracy facial recognition models on resource-constrained IoT devices remains a significant challenge. In this paper, proposed an optimized convolutional neural network (CNN) model for facial biometric authentication in IoT environments. The optimization techniques include model pruning, quantization, and the use of lightweight CNN architectures to ensure computational efficiency while maintaining high accuracy. The proposed model is evaluated on widely used benchmark datasets, including labeled faces in the wild (LFW) and CelebA. Experimental results show that the optimized CNN achieves state-of-the-art performance, with 96.7% accuracy on LFW and 95.2% on CelebA. These results confirm that the proposed approach consistently outperforms baseline models across all evaluation settings.
Full Text:
PDFReferences
M. Moradi, M. Moradkhani, and M. B. Tavakoli, “Security-level improvement of IoT-based systems using biometric features,” Wirel. Commun. Mob. Comput., 2022(1), pp. 1–15, 2022.
F. Farid, M. Elkhodr, F. Sabrina, F. Ahamed, and E. Gide, “A smart biometric identity management framework for personalised IoT and cloud computing-based healthcare services,” Sensors, 21(2), p. 552, 2021.
U. Sumalatha, K. K. Prakasha, S. Prabhu, and V. C. Nayak,
“A Comprehensive Review of Unimodal and Multimodal Fingerprint Biometric Authentication Systems: Fusion, Attacks, and Template Protection,” IEEE Access, vol. 5, pp. 220362–72 2024.
R. R. Rawat et al., “Deep learned tissue ‘fingerprints’ classify breast cancers by ER/PR/Her2 status from H&E images,” Sci. Rep., 10(1), pp. 1–13, 2020.
Y. Moon, I. Ryoo, and S. Kim, “Face Antispoofing Method Using Colour Texture Segmentation on FPGA,” Secur. Commun. Networks, vol. 2021, p. 9939232, 2021,
S. Girmay, F. Samsom, and A. M. Khattak, “AI-based Login System using Facial Recognition,” in 2021 5th Cyber Security in Networking Conference (CSNet), UAE, 2021, pp. 107–109.
N. H. Kamarudin, N. H. Suhaimi, F. A. Nor Rashid, M. N. Khalid, and F. Mohd Ali, “Exploring Authentication Paradigms in the Internet of Things: A Comprehensive Scoping Review,” Symmetry, 16(2), p. 171, 2024.
M. Y. S. Krishna, A. Arya, S. Ansari, S. Awasya, J. Sushakar, and N. Uikey, “Real Time Door Unlocking System using Facial Biometrics based on IoT and Python,” in 2023 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 2023, pp. 1–5.
B. Singh, R. Lal, and S. Singla, “A Secure Authentication mechanism for accessing IoT devices through Mobile App,” in 2022 International Conference on Computational Modelling, Simulation and Optimization, Thailand, 2022, pp. 274–278.
A. J. Prakash, K. K. Patro, S. Samantray, P. Pławiak, and M. Hammad, “A Deep Learning Technique for Biometric Authentication Using ECG Beat Template Matching,” Information, 14(2), article 65, 2023.
K. Sundararajan and D. L. Woodard, “Deep learning for biometrics: A survey,” ACM Comput. Surv., 51(3), pp. 1–34, 2018.
W. Yan, J. Tang, and S. Stucki, “Design and implementation of a lightweight deep CNN-based plant biometric authentication system,” IEEE Access, vol. 2, pp. 120364–120370, 2023.
D. A. Muhtasim, M. I. Pavel, and S. Y. Tan, “A patch-based CNN built on the VGG-16 architecture for real-time facial liveness detection,” Sustainability, 14(16), p. 10024, 2022.
Ş. Kiliç, I. Askerzade, and Y. Kaya, “Using ResNet transfer deep learning methods in person identification according to physical actions,” IEEE Access, vol. 8, pp. 220364–220373, 2020.
A. Ullah, H. Elahi, Z. Sun, A. Khatoon, and I. Ahmad, “Comparative analysis of AlexNet, ResNet18, and SqueezeNet with diverse modification and arduous implementation,” Arab. J. Sci. Eng., 47(2), pp. 2397–2417, 2022.
L. Krishnamoorthy and A. S. Raju, “Deep Ensemble of VGG, ResNet and Inception for Multimodal Authentication System,” in 2024 Second International Conference on Networks, Multimedia and Information Technology, 2024, pp. 1–6.
A. Anand, S. Rani, D. Anand, H. M. Aljahdali, and D. Kerr, “An efficient CNN-based deep learning model to detect malware attacks (CNN-DMA) in 5G-IoT healthcare applications,” Sensors, 21(19), p. 6346, 2021.
Y. Jiang et al., “Model pruning enables efficient federated learning on edge devices,” IEEE Trans. Neural Networks Learn. Syst., 34(12), pp. 10374–10386, 2022.
J. Yang et al., “Quantization networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, CA, USA, 2019, pp. 7308–7316.
T. N. Abu-Jamie and S. S. Abu-Naser, “Classification of sign-language using MobileNet-deep learning,” International Journal of Academic Information Systems Research, 6(8), pp.25-34, 2022.
T. Bagchi et al., “Intelligent security system based on face recognition and IoT,” Mater. Today Proc., vol. 62, pp. 2133–2137, 2022.
A. Sardar, S. Umer, R. K. Rout, S.-H. Wang, and M. Tanveer, “A secure face recognition for IoT-enabled healthcare system,” ACM Trans. Sens. Networks, 19(3), pp. 1–23, 2023.
M. Masud et al., “Deep learning-based intelligent face recognition in IoT-cloud environment,” Comput. Commun., vol. 152, pp. 215–222, 2020.
G. Muhammad, M. Alsulaiman, S. U. Amin, A. Ghoneim, and M. F. Alhamid, “A facial-expression monitoring system for improved healthcare in smart cities,” IEEE Access, vol. 5, pp. 10871–10881, 2017.
F. Alshehri and G. Muhammad, “A comprehensive survey of the Internet of Things (IoT) and AI-based smart healthcare,” IEEE Access, vol. 9, pp. 3660–3678, 2020.
E. Learned-Miller, G. B. Huang, A. RoyChowdhury, H. Li, and G. Hua, “Labeled faces in the wild: A survey,” Adv. Face Detect. Facial Image Anal., pp. 189–248, 2016.
Z. Liu, P. Luo, X. Wang, and X. Tang, “Large-scale celebfaces attributes (celeba) dataset,” Retrieved August, vol. 15, no. 2018, p. 11, 2018.
R. Indraswari, “ScienceDirect ScienceDirect Melanoma based on MobileNetV2 network Melanoma image image classification classification based MobileNetV2 network,” Procedia Comput. Sci., vol. 197, pp. 198–207, 2022.
E. Upton and G. Halfacree, Raspberry Pi user guide. John Wiley & Sons, 2016. ISBN 978-1119264361
T. Anees, Q. Habib, A. S. Al-Shamayleh, W. Khalil, M. A. Obaidat, and A. Akhunzada, “The integration of WoT and edge computing: Issues and challenges,” Sustainability, 15(7), p. 5983, 2023.
O. M. Parkhi, A. Vedaldi, and A. Zisserman, “Deep face recognition,” Proceedings of the British Machine Vision Conference (BMVC), Swansea, UK, September 7–10, 2015. British Machine Vision Association, 2015.
M. I. Ardiawan and G. P. K. Negarara, “A Comparative Analysis of FaceNet, VGGFace, and GhostFaceNets Face Recognition Algorithms For Potential Criminal Suspect Identification,” J. Appl. Artif. Intell., 5(2), pp. 34–49, 2024.
W. Liu, Y. Wen, B. Raj, R. Singh, and A. Weller, “Sphereface revived: Unifying hyperspherical face recognition,” IEEE Trans. Pattern Anal. Mach. Intell., 45(2), pp. 2458–2474, 2022.
H. Wang et al., “Cosface: Large margin cosine loss for deep face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, Utah, 2018, pp. 5265–5274.
URN: https://sloi.org/urn:sl:tjoee102364
Copyright (c) 2025 Turkish Journal of Electromechanics and Energy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Indexed in:
