The problem of building a face recognition pipeline faces numerous challenges such as changes in lighting, pose, and facial expressions. The main stages of the pipeline include detection, alignment, feature extraction, and face representation. Each of these stages is critically important for achieving accurate recognition. The article analyzes and compares modern algorithms and models for face detection and recognition in terms of their ability to correctly identify true positives (TP) and true negatives (TN) while minimizing false negatives (FN) and false positives (FP) in facial recognition. Classical algorithms and lightweight models, such as MediaPipe, offer the highest speeds but sacrifice some accuracy. Conversely, heavier models like RetinaFace deliver greater accuracy at the expense of speed. For systems prioritizing maximum detection accuracy and minimizing missed faces, models like DSFD or RetinaFace-Resnet50 are recommended, despite their slow performance and unsuitability for real-time detection. If the primary goal is maximum detection speed and occasional missed faces in uncontrolled conditions are acceptable, an SSD face recognition solution is preferable. For applications requiring a balanced approach to speed and accuracy, the RetinaFace-MobilenetV1 model is optimal in terms of real-time detection speed and satisfactory accuracy. The ArcFace model demonstrates superior performance with a TP rate of 0.92 and a TN rate of 0.91, indicating a high accuracy in both identifying the correct person and rejecting mismatched images. ArcFace also maintains a low FP rate of 0.09. FaceNet follows with a TP rate of 0.89 and an impressive TN rate of 0.94, showcasing its proficiency in avoiding incorrect matches. In contrast, VGGFace, DeepFace, and OpenFace show moderate TP rates between 0.61 and 0.78, coupled with higher FN and FP rates. The DeepID model exhibits the lowest performance, with a TP rate of 0.47 and a TN rate of 0.60, reflecting substantial difficulties in accurate identification. The conclusions emphasize the importance of selecting models based on accuracy, speed, and resource requirements, suggesting RetinaFace and ArcFace/FaceNet as good trade-off options.
[1] Y. Feng, S. Yu, H. Peng, Y. -R. Li and J. Zhang, "Detect Faces Efficiently: A Survey and Evaluations," in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 4, no. 1, pp. 1-18, Jan. 2022, doi: 10.1109/TBIOM.2021.3120412.
[2] 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, no. 10, pp. 1499–1503, 2016.
[3] B. Meden et al., "Privacy–Enhancing Face Biometrics: A Comprehensive Survey," in IEEE Transactions on Information Forensics and Security, vol. 16, pp. 4147-4183, 2021, doi: 10.1109/TIFS.2021.3096024.
[4] T. Bezdan, N. Bačanin Džakula, “Convolutional Neural Network Layers and Architectures,” in Sinteza 2019 - International Scientific Conference on Information Technology and Data Related Research, Belgrade, Singidunum University, Serbia, 2019, pp. 445-451. doi:10.15308/Sinteza-2019-445-451.
[5] Yi-Qing Wang, An Analysis of the Viola-Jones Face Detection Algorithm, Image Processing On Line, 4 (2014), pp. 128–148. doi:10.5201/ipol.2014.104.
[6] RetinaFace: Single-stage Dense Face Localisation in the Wild, Jiankang Deng, Jia Guo, Yuxiang Zhou, Jinke Yu, Irene Kotsia, Stefanos Zafeiriou, 2019. doi:10.48550/arXiv.1905.00641.
[7] Face Image Feature Extraction based on Deep Learning Algorithm, Qing Kuang, 2021. doi:10.1088/1742-6596/1852/3/032040.
[8] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, "SSD: Single Shot MultiBox Detector," in *Lecture Notes in Computer Science*, Springer International Publishing, 2016, pp. 21–37, doi: 10.1007/978-3-319-46448-0_2.
[9] N. Zhang, J. Luo and W. Gao, "Research on Face Detection Technology Based on MTCNN," 2020 International Conference on Computer Network, Electronic and Automation (ICCNEA), Xi'an, China, 2020, pp. 154-158, doi: 10.1109/ICCNEA50255.2020.00040.
[10]J. Li et al., "DSFD: Dual Shot Face Detector," 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 5055-5064, doi: 10.1109/CVPR.2019.00520.
[11]M. K. Hasan, M. S. Ahsan, S. H. S. Newaz, and G. M. Lee, "Human face detection techniques: A comprehensive review and future research directions," *Electronics*, vol. 10, no. 19, p. 2354, 2021, doi: 10.3390/electronics10192354.
[12]B. Dey, K. Khalil, A. Kumar and M. Bayoumi, "A Reversible-Logic based Architecture for VGGNet," 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), Dubai, United Arab Emirates, 2021, pp. 1-4, doi: 10.1109/ICECS53924.2021.9665605.
[13]F. Schroff, D. Kalenichenko and J. Philbin, "FaceNet: A unified embedding for face recognition and clustering," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 815-823, doi: 10.1109/CVPR.2015.7298682.
[14]B. Amos, B. Ludwiczuk, and M. Satyanarayanan, "OpenFace: A general-purpose face recognition library with mobile applications," in *Proceedings of the 2016 Conference on Vision and Pattern Recognition* (CVPR), 2016.
[15]Y. Taigman, M. Yang, M. Ranzato and L. Wolf, "DeepFace: Closing the Gap to Human-Level Performance in Face Verification," 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 1701-1708, doi: 10.1109/CVPR.2014.220.
[16]W. Ouyang, X. Wang, X. Zeng, S. Qiu, P. Luo, Y. Tian, H. Li, S. Yang, Z. Wang, C.-C. Loy, and X. Tang, "DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection," arXiv preprint arXiv:1412.5661, 2015.
[17]ArcFace: Additive Angular Margin Loss for Deep Face Recognition Jiankang Deng, Jia Guo, Jing Yang, Niannan Xue, Irene Kotsia, Stefanos Zafeiriou, 2018., doi: 10.48550/arXiv.1801.07698.