MFCosface: A Masked-Face Recognition Algorithm Based on Large Margin Cosine Loss
Source abstract
Abstract
The world today is being hit by COVID-19. As opposed to fingerprints and ID cards, facial recognition technology can effectively prevent the spread of viruses in public places because it does not require contact with specific sensors. However, people also need to wear masks when entering public places, and masks will greatly affect the accuracy of facial recognition. Accurately performing facial recognition while people wear masks is a great challenge. In order to solve the problem of low facial recognition accuracy with mask wearers during the COVID-19 epidemic, we propose a masked-face recognition algorithm based on large margin cosine loss (MFCosface). Due to insufficient masked-face data for training, we designed a masked-face image generation algorithm based on the detection of the detection of key facial features. The face is detected and aligned through a multi-task cascaded convolutional network; and then we detect the key features of the face and select the mask template for coverage according to the positional information of the key features. Finally, we generate the corresponding masked-face image. Through analysis of the masked-face images, we found that triplet loss is not applicable to our datasets, because the results of online triplet selection contain fewer mask changes, making it difficult for the model to learn the relationship between mask occlusion and feature mapping. We use a large margin cosine loss as the loss function for training, which can map all the feature samples in a feature space with a smaller intra-class distance and a larger inter-class distance. In order to make the model pay more attention to the area that is not covered by the mask, we designed an Att-inception module that combines the Inception-Resnet module and the convolutional block attention module, which increases the weight of any unoccluded area in the feature map, thereby enlarging the unoccluded area’s contribution to the identification process. Experiments on several masked-face datasets have proved that our algorithm greatly improves the accuracy of masked-face recognition, and can accurately perform facial recognition with masked subjects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face recognition and analysis · Face and Expression Recognition · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information and Computer, Taiyuan University of Technology, Taiyuan 030024, China
College of Software, Taiyuan University of Technology, Taiyuan 030024, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Shanxi Province
References (46)
Show source-provided references
1. Sparse representation for based on constraint sampling and face alignment10.1109/TST.2013.6449409 ↗
2. Shenvi, D.R., and Shet, K. (2021, January 25–27). Cnn based covid-19 prevention system. Proceedings of the 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India.10.1109/ICAIS50930.2021.9396004 ↗
3. Yin, X., Yu, X., Sohn, K., Liu, X., and Chandraker, M. (2019, January 15–20). Feature transfer learning for face recognition with under-represented data. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00585 ↗
4. Hu, G., Yang, Y., Yi, D., Kittler, J., Li, S., and Hospedales, T. (2015, January 7–13). When face recognition meets with deep learning: An evaluation of convolutional neural networks for face recognition. Proceedings of the IEEE International Conference on Computer Vision Workshop, Santiago, Chile.10.1109/ICCVW.2015.58 ↗
5. A review on face recognition systems: Recent approaches and challenges10.1007/s11042-020-09261-2 ↗
6. Sun, Y., Liang, D., Wang, X., and Tang, X. (2015). DeepID3: Face Recognition with Very Deep Neural Networks. arXiv.
7. Deng, H., Feng, Z., Liu, Y., Luo, D., Yang, X., and Li, H. (2020, January 5–6). Face recognition algorithm based on weighted intensity pcnn. Proceedings of the 2020 Eighth International Conference on Advanced Cloud and Big Data (CBD), Taiyuan, China.10.1109/CBD51900.2020.00045 ↗
8. Yang, M., Zhang, L., Yang, J., and Zhang, D. (2011, January 20–25). Robust sparse coding for face recognition. Proceedings of the Computer Vision and Pattern Recognition, Colorado Springs, CO, USA.10.1109/CVPR.2011.5995393 ↗
9. Structured occlusion coding for robust face recognition10.1016/j.neucom.2015.05.132 ↗
10. Wu, C., and Ding, J. (2019). Occluded face recognition using low-rank regression with generalized gradient direction. arXiv.10.1016/j.patcog.2018.03.016 ↗
11. Dong, J., Zheng, H., and Lian, L. (2019, January 15–20). Low-rank laplacian-uniform mixed model for robust face recognition. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01217 ↗
12. Shi, Y., Yu, X., Sohn, K., Chandraker, M., and Jain, A. (2020, January 13–19). Towards universal representation learning for deep face recognition. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00685 ↗
13. Densely connected convolutional networks face recognition algorithm based on weighted feature fusion
14. Song, L., Gong, D., Li, Z., Liu, C., and Liu, W. (November, January 27). Occlusion robust face recognition based on mask learning with pairwise differential siamese network. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.
15. Dictionary representation of deep features for occlusion-robust face recognition10.1109/ACCESS.2019.2901376 ↗
16. Towards nir-vis masked face recognition10.1109/LSP.2021.3071663 ↗
17. Wang, Z., and Kim, T.S. (2021, January 13–16). Learning to recognize masked faces by data synthesis. Proceedings of the 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Jeju Island, Korea.10.1109/ICAIIC51459.2021.9415252 ↗
18. Amin, M.I., Hafeez, M.A., Touseef, R., and Awais, Q. (2021, January 23–24). Person identification with masked face and thumb images under pandemic of covid-19. Proceedings of the 2021 7th International Conference on Control, Instrumentation and Automation (ICCIA), Tabriz, Iran.10.1109/ICCIA52082.2021.9403577 ↗
19. Robust nuclear norm-based matrix regression with applications to robust face recognition10.1109/TIP.2017.2662213 ↗
20. Ejaz, M., Islam, M., Sifatullah, M., and Sarker, A. (2019, January 3–5). Implementation of principal component analysis on masked and non-masked face recognition. Proceedings of the 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh.10.1109/ICASERT.2019.8934543 ↗
21. Research on inception module incorporated siamese convolutional neural networks to realize face recognition10.1109/ACCESS.2019.2963211 ↗
22. Face alignment in-the-wild: A Survey10.1016/j.cviu.2017.08.008 ↗
23. Georgios, T., and Maja, P. (2013, January 1–8). Optimization Problems for Fast AAM Fitting in-the-Wild. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia.
24. Epameinondas, A., Joan, A., and Stefanos, Z. (2015, January 7–12). Active Pictorial Structures. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.
25. Joint face detection and alignment using multitask cascaded convolutional networks10.1109/LSP.2016.2603342 ↗
26. Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., and Zhou, Q. (2018, January 18–23). Look at Boundary: A Boundary-Aware Face Alignment Algorithm. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00227 ↗
27. Kowalski, M., Naruniec, J., and Trzcinski, T. (2017, January 21–26). Deep alignment network: A convolutional neural network for robust face alignment. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.10.1109/CVPRW.2017.254 ↗
28. Huang, Z., Zhang, J., and Shan, H. (2021). When age-invariant face recognition meets face age synthesis: A multi-task learning framework. arXiv.10.1109/CVPR46437.2021.00720 ↗
29. Zhong, Y., Deng, W., Wang, M., Hu, J., Peng, J., Tao, X., and Huang, Y. (2019, January 15–20). Unequal-training for deep face recognition with long-tailed noisy data. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00800 ↗
30. Wen, Y., Zhang, K., Li, Z., and Qiao, Y. (2016, January 11–12). A discriminative feature learning approach for deep face recognition. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46478-7_31 ↗
31. Liu, W., Wen, Y., Yu, Z., and Yang, M. (2016). Large-margin softmax loss for convolutional neural networks. arXiv.
32. Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., and Song, L. (2017, January 21–26). Sphereface: Deep hypersphere embedding for face recognition. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.713 ↗
33. Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., Li, Z., and Liu, W. (2018, January 18–23). Cosface: Large margin cosine loss for deep face recognition. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00552 ↗
34. Deng, J., Guo, J., Xue, N., and Zafeiriou, S. (2019, January 15–20). Arcface: Additive angular margin loss for deep face recognition. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00482 ↗
35. Tay, C.-P., Roy, S., and Yap, K.-H. (2019, January 15–20). Aanet: Attribute attention network for person re-identifications. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00730 ↗
36. Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 15–20). Dual attention network for scene segmentation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00326 ↗
37. Gao, Z., Xie, J., Wang, Q., and Li, P. (2019, January 15–20). Global second-order pooling convolutional networks. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00314 ↗
38. Woo, S., Park, J., Lee, J., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
39. Wang, X., Girshick, R., Mulam, H., and He, K. (2018, January 18–23). Non-local neural networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00813 ↗
40. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
41. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13–19). Eca-net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
42. Kazemi, V., and Sullivan, J. (2014, January 23–28). One millisecond face alignment with an ensemble of regression trees. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.241 ↗
43. Anwar, A., and Raychowdhury, A. (2020). Masked face recognition for secure authentication. arXiv.
44. Schroff, F., Kalenichenko, D., and Philbin, J. (2015, January 7–12). Facenet: A unified embedding for face recognition and clustering. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298682 ↗
45. Damer, N., Grebe, J.H., Chen, C., Boutros, F., Kirchbuchner, F., and Kuijper, A. (2020). The effect of wearing a mask on face recognition performance: An exploratory study. arXiv.
46. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016, January 12–17). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.10.1609/aaai.v31i1.11231 ↗