Abstract
The COVID-19 epidemic has made us all to understand that using face masks is one of the best ways to save ourselves from infections. Face recognition techniques often focus on the essential facial landmarks such as nose, mouth and eyes. Removing masks in airports or other public places for authentication will raise the danger of virus infection, and this will pose a challenge to the existing face recognition systems. This paper presents a novel approach to recognize masked faces that combines cropping the unmasked half of the face (the upper part of a face) image using a vision transformer model. Various scenarios are investigated in this paper. The model is trained using the images of the upper half of the face and tested on the same, full-face images with a mask and full face images without a mask. The experiments on the standard datasets, namely RMFRD, MLFW and masked CASIA-WebFace show that the proposed approach improves masked face recognition significantly compared to the existing methods. The explainability of the proposed model is demonstrated using a class activation map.
Similar content being viewed by others
Data Availability
Raw data were available at the https://www.kaggle.com/datasets/ntl0601/casia-webface, https://www.kaggle.com/datasets/muhammeddalkran/lfw-simulated-masked-face-dataset and https://www.kaggle.com/datasets/muhammeddalkran/masked-facerecognition. Derived data supporting the findings of this study are available from the corresponding author on request. The created dataset for testing the model in real-time is having privacy issues and it can not be made public.
References
Ali W, Tian W, Din SU, Iradukunda D, Khan AA (2021) Classical and modern face recognition approaches: a complete review. Multimed Tools Appl 80:4825–4880
Turk M (1991) Pentland. eigenfaces for recognition. J Cogn Neurosci 4:72–86
Yang M, Zhang L, Shiu SCK, Zhang D (2012) Monogenic binary coding: An efficient local feature extraction approach to face recognition. IEEE Trans Inf Forensics Secur 7(6):1738–1751
Cao Q, Shen L, Xie W, Parkhi OM, Zisserman A (2018) Vggface2: A dataset for recognising faces across pose and age. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) 67–74. IEEE
Zhang G, Huang X, Li SZ, Wang Y, Wu X (2004) Boosting local binary pattern (lbp)-based face recognition. In: Chinese Conference on Biometric Recognition, pp. 179–186. Springer
Sun Y, Chen Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. Advances in neural information processing systems 27
Taigman Y, Yang M, Ranzato M, Wolf L (2014) Deepface: Closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 1701–1708
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 815–823
Wang H, Wang Y, Zhou Z, Ji X, Gong D, Zhou J, Li Z, Liu W (2018) Cosface: Large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 5265–5274
Deng J, Guo J, Xue N, Zafeiriou S (2019) Arcface: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 4690–4699
Li Y, Guo K, Lu Y, Liu L (2021) Cropping and attention based approach for masked face recognition. Appl Intell 51(5):3012–3025
Alzu’bi A, Albalas F, Al-Hadhrami T, Younis LB, Bashayreh A, (2021) Masked face recognition using deep learning: A review. Electronics 10(21):2666
Liu W, Wen Y, Yu Z, Li M, Raj B, Song L (2017) Sphereface: Deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929
Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213–229. Springer
Zhu Z, Huang G, Deng J, Ye Y, Huang J, Chen X, Zhu J, Yang T, Guo J, Lu J et al (2021) Masked face recognition challenge: The webface260m track report. arXiv:2108.07189
Deng J, Guo J, An X, Zhu Z, Zafeiriou S (2021) Masked face recognition challenge: The insightface track report. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1437–1444
Wang Z, Wang G, Huang B, Xiong Z, Hong Q, Wu H, Yi P, Jiang K, Wang N, Pei Y et al (2020) Masked face recognition dataset and application. arXiv:2003.09093
Ge S, Li J, Ye Q, Luo Z (2017) Detecting masked faces in the wild with llecnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2682–2690
Anwar A, Raychowdhury A (2020) Masked face recognition for secure authentication. arXiv:2008.11104
Zhang Y, Wang X, Shakeel MS, Wan H, Kang W (2022) Learning upper patch attention using dual-branch training strategy for masked face recognition. Pattern Recognition 126:108522
Ding F, Peng P, Huang Y, Geng M, Tian Y (2020) Masked face recognition with latent part detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2281–2289
Hariri W (2022) Efficient masked face recognition method during the covid-19 pandemic. Signal, image and video processing 16(3):605–612
Du H, Shi H, Liu Y, Zeng D, Mei T (2021) Towards nir-vis masked face recognition. IEEE Signal Process Lett 28:768–772
Golwalkar R, Mehendale N (2022) Masked-face recognition using deep metric learning and facemasknet-21. Applied Intelligence 1–12
Geng M, Peng P, Huang Y, Tian Y (2020) Masked face recognition with generative data augmentation and domain constrained ranking. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2246–2254
Kumar S, Yadav D, Gupta H, Kumar M, Verma OP (2022) Towards smart surveillance as an aftereffect of covid-19 outbreak for recognition of face masked individuals using yolov3 algorithm. Multimedia Tools and Applications 1–23
Yi D, Lei Z, Liao S, Li SZ (2014) Learning face representation from scratch. arXiv:1411.7923
Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499–1503
Ku H, Dong W (2020) Face recognition based on mtcnn and convolutional neural network. Frontiers in Signal Processing 4(1):37–42
Zhong Y, Deng W (2021) Face transformer for recognition. arXiv:2103.14803
PyTorch: TORCHVISION.MODELS. https://pytorch.org/vision/0.8/models.html
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929
Yin B, Tran L, Li H, Shen X, Liu X (2019) Towards interpretable face recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9348–9357
Song L, Gong D, Li Z, Liu C, Liu W (2019) Occlusion robust face recognition based on mask learning with pairwise differential siamese network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 773–782
Shuai Z, Feng S (2021) Face recognition method of mask occlusion. In: 2021 IEEE International Conference on Smart Internet of Things (SmartIoT), pp. 82–88. IEEE
Wu G (2021) Masked face recognition algorithm for a contactless distribution cabinet. Mathematical problems in engineering 2021
Chen HQ, Xie K, Li MR, Wen C, He JB (2022) Face recognition with masks based on spatial fine-grained frequency domain broadening. Ieee Access 10:75536–75548
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
T, A., V, M. Explainable masked face recognition. Multimed Tools Appl 83, 31123–31138 (2024). https://doi.org/10.1007/s11042-023-16571-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16571-8