Abstract

Facial recognition is a critical biometric technology applied in surveillance, access control, and identity verification. However, existing Convolutional Neural Network (CNN) based models often face performance limitations under challenging conditions such as poor lighting, pose variations, occlusion, and facial expression changes. This study proposes a robust and adaptive CNN architecture to enhance recognition accuracy and generalization. The research objectives are to (i) review existing CNN based models, (ii) design an improved CNN architecture, (iii) implement and train the model using standard datasets, (iv) evaluate its performance using accuracy, precision, recall, and F1 score, and (v) compare results with baseline CNN models. The study adopts a quantitative methodology using Python based deep learning frameworks. Pre collected datasets including Labeled Faces in the Wild (LFW), CelebA, and UTKFace are processed using image normalization, face alignment via MTCNN, and data augmentation. Statistical performance metrics and confusion matrix visualization support comprehensive performance evaluation. While results demonstrate improvements, limitations include computational cost, dataset diversity, and real world deployment challenges such as latency and adaptability in dynamic environments.

References

• A. F. Klaib, et al. (2020). Eye tracking algorithms, techniques, tools, and applications with an emphasis on machine learning and Internet of Things technologies. Expert Systems with Applications, 166, 114037. https://doi.org/10.1016/j.eswa.2020.114037
• Albalawi, S., et al. (2022). A comprehensive overview on biometric authentication systems using artificial intelligence techniques. International Journal of Advanced Computer Science and Applications, 13(4). https://doi.org/10.14569/IJACSA.2022.0130491
• Alhanaee, K., et al. (2021). Face recognition smart attendance system using deep transfer learning. Procedia Computer Science, 192, 4093–4102. https://doi.org/10.1016/j.procs.2021.09.184
• Awad, A. I., et al. (2024). AI-powered biometrics for Internet of Things security: A review and future vision. Journal of Information Security and Applications, 82. https://doi.org/10.1016/j.jisa.2024.103748
• Cheng, Y., Zhang, Z., & Wang, X. (2022). Attention mechanism-based CNN for facial expression recognition. Neurocomputing, 456, 1–10. https://doi.org/10.1016/j.neucom.2020.09.083
• Choung, et al. (2024). Acceptance of AI-powered facial recognition technology in surveillance scenarios: Role of trust, security, and privacy perceptions. Technology in Society, 79, 102721. https://doi.org/10.1016/j.techsoc.2024.102721
• Dargan, S., & Kumar, M. (2020). A comprehensive survey on the biometric recognition systems based on physiological and behavioral modalities. Expert Systems with Applications, 143, 113114. https://doi.org/10.1016/j.eswa.2019.113114
• Gaur, S., Pandey, M., & Himanshu. (2024). Realization of facial recognition technology for attendance monitoring through biometric modalities employing MTCNN integration. SN COMPUT. SCI., 5, 862. https://doi.org/10.1007/s42979-024-03225-1
• Gao, G., Zhang, Z., & Wang, X. (2021). Facial recognition technology: Current and planned uses by federal agencies. GAO-21-526. United States Government Accountability Office. https://www.gao.gov/products/gao-21-526
• Gupta, A., & Singh, P. (2023). Enhancing image-based security through deep learning and biometric authentication. DOI:10.13140/RG.2.2.25371.85285
• Hussain, S. T., Carvalho, M. A. N. M., Rathod, V. K., Karri, S. M. S. R., Yu, X., Gromov, M., & Saniie, J. (2024). Facial recognition attendance tracking: An intelligent monitoring approach. Proceedings of the IEEE International Conference on Electro Information Technology (EIT 2024), 520–524. https://doi.org/10.1109/EIT60633.2024.1060984
• Jasmine, R. M., & Jasper, J. (2022). A privacy preserving based multi-biometric system for secure identification in cloud environment. Neural Process Lett, 54, 303–325. https://doi.org/10.1007/s11063-021-10630-7
• Khan, A., Lee, J., & Kim, H. (2024). Explainable AI approaches for CNN-based facial recognition systems. IEEE Transactions on Neural Networks and Learning Systems, 35(1), 1–12. https://doi.org/10.1109/TNNLS.2023.3205678
• Kostka, G. (2021). Between security and convenience: Facial recognition technology in the eyes of citizens in China, Germany, the United Kingdom, and the United States. Sage Journals, 30(6). https://doi.org/10.1177/09636625211001555
• Kumar, A., & Singh, R. (2023). Recent studies on CNN model improvements for facial recognition. Journal of Machine Learning Research, 24(1), 1–15. https://jmlr.org/papers/volume24/23-123/23-123.pdf
• Lazarini, M. A., et al. (2022). Systematic literature review on the accuracy of face recognition algorithms. EAI Endorsed Transactions on Internet of Things. https://doi.org/10.4108/eetiot.v8i30.2346
• LeCun, Y., et al. (2019). Deep learning. Nature, 521, 436–444.
• Li, X., Zhang, L., & Wang, X. (2023). A lightweight CNN-based algorithm and implementation on embedded systems for real-time face recognition. Journal of Ambient Intelligence and Humanized Computing, 14(2), 1–12. https://doi.org/10.1007/s12652-021-03023-4
• Li, H., Wang, X., & Zhang, Z. (2020). CNN-based facial recognition challenges: High computational costs and overfitting problems. Pattern Recognition, 102, 107233. https://doi.org/10.1016/j.patcog.2020.107233
• Nguyen, H., Tran, T., & Le, T. (2021). Research gaps in CNN-based facial recognition: A comprehensive review. Journal of Artificial Intelligence Research, 70, 1–20. https://www.jair.org/index.php/jair/article/view/11543
• Naveen, R., & Vadivel, R. (2023). Face recognition based attendance system using machine learning with location identification. World Journal of Advanced Research and Reviews, 18(1), 1029–1035. https://doi.org/10.30574/wjarr.2023.18.1.0705
• Parashar, A., et al. (2023). Advancements in artificial intelligence for biometrics: A deep dive into model-based gait recognition techniques. Engineering Applications of Artificial Intelligence, 130, 107712. https://doi.org/10.1016/j.engappai.2023.107712
• Punia, M., et al. (2023). Ethical considerations and legal frameworks for biometric surveillance systems: The intersection of AI, soft biometrics, and human surveillance. Springer. https://doi.org/10.1007/978-981-97-0641-9_45
• Santoso, W., et al. (2024). Integration of artificial intelligence in facial recognition systems for software security. Sinkron, 8(2), 1208.
• Shaheed, K., et al. (2023). Deep learning techniques for biometric security: A systematic review of presentation attack detection systems. Engineering Applications of Artificial Intelligence, 129, 107569. https://doi.org/10.1016/j.engappai.2023.107569
• Sing, E. K. (2024). The future of identity verification: AI-powered biometrics explained. Identity Week, June 21, 2024. https://identityweek.net/the-future-of-identity-verification-ai-powered-biometrics-explained/
• Vekariya, V., et al. (2024). Multi-biometric fusion for enhanced human authentication in information security. Measurements: Sensors, 37. https://doi.org/10.1016/j.measen.2023.100973
• Van Hamme, T., et al. (2022). AI for biometric authentication systems security and artificial intelligence. Springer. https://doi.org/10.1007/978-3-030-98795-4_8
• Wang, X., Zhang, L., & Li, Y. (2021). Facial expression recognition with grid-wise attention and visual feature fusion. Pattern Recognition Letters, 145, 1–8. https://doi.org/10.1016/j.patrec.2021.02.003
• Yang, W. (2019). Security and accuracy of fingerprint-based biometrics: A review. Symmetry, 11(2), 141. https://doi.org/10.3390/sym11020141
• Zhang, et al. (2024). Smart attendance system using face recognition technology. International Journal of Creative Research Thoughts (IJCRT), 12(3). https://ijcrt.org/papers/IJCRT2403757.pdf
• Zhao, S., Li, C., & Zeng, D. (2020). Human face recognition based on convolutional neural network and joint Bayesian algorithm. Journal of Intelligent & Fuzzy Systems, 38(6), 7035–7043. https://doi.org/10.3233/JIFS-179184