Face Spoofing Detection with Stacking Ensembles in Work Time Registration System
Source abstract
Abstract
This paper introduces a passive face-authenticity detection system, designed for integration into an employee work time registration platform. The system is implemented as a stacking ensemble of multiple models. Each model independently assesses whether a camera is capturing a live human face or a spoofed representation, such as a photo or video. The ensemble comprises a convolutional neural network (CNN), a smartphone bezel-detection algorithm to identify faces displayed on electronic devices, a face context analysis module, and additional CNNs for image processing. The outputs of these models are aggregated by a neural network that delivers the final classification decision. We examined various combinations of models within the ensemble and compared the performance of our approach against existing methods through experimental evaluation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face recognition and analysis · Biometric Identification and Security · User Authentication and Security Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Automatics, University of Bielsko-Biala, 43-309 Bielsko-Biała, Poland
inEwi, sp. z o. o., ul. 1 Maja 15, 43-300 Bielsko-Biała, Poland
Funding
National Centre for Research and Development of Poland (NCBiR)
References (45)
Show source-provided references
1. Apple Inc. (2024, April 14). About Face ID Advanced Technology. Available online: https://support.apple.com/en-us/102381.
2. Bazarevsky, V., Kartynnik, Y., Vakunov, A., Raveendran, K., and Grundmann, M. (2019). BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs. arXiv.
3. Deng, J., Guo, J., and Zafeiriou, S. (2018). ArcFace: Additive Angular Margin Loss for Deep Face Recognition. arXiv.10.1109/CVPR.2019.00482 ↗
4. Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020, January 13–19). RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00525 ↗
5. Timoshenko, D., Simonchik, K., Shutov, V., Zhelezneva, P., and Grishkin, V. (2019, January 19–20). Large Crowdcollected Facial Anti-Spoofing Dataset. Proceedings of the 2019 Computer Science and Information Technologies (CSIT), Chennai, India.10.1109/CSITechnol.2019.8895208 ↗
6. Zhang, Y., Yin, Z., Li, Y., Yin, G., Yan, J., Shao, J., and Liu, Z. (2020, January 23–28). CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.10.1007/978-3-030-58610-2_5 ↗
7. Taigman, Y., Yang, M., Ranzato, M.A., and Wolf, L. (2014, January 23–28). Deepface: Closing the gap to human-level performance in face verification. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.220 ↗
8. Sun, Y., Wang, X., and Tang, X. (2015, January 7–12). Deeply learned face representations are sparse, selective, and robust. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298907 ↗
9. Face Spoof Detection Using VGG-Face Architecture10.1088/1742-6596/1917/1/012010 ↗
10. 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 Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.713 ↗
11. de Freitas Pereira, T., Anjos, A., De Martino, J.M., and Marcel, S. (2012, January 5–6). Lbp-top based countermeasure against face spoofing attacks. Proceedings of the ACCV, Daejeon, Republic of Korea.10.1007/978-3-642-37410-4_11 ↗
12. Boulkenafet, Z., Komulainen, J., and Hadid, A. (2015, January 27–30). Face anti-spoofing based on color texture analysis. Proceedings of the ICIP, Quebec City, QC, Canada.10.1109/ICIP.2015.7351280 ↗
13. Secure face unlock: Spoof detection on smartphones10.1109/TIFS.2016.2578288 ↗
14. Face antispoofing using speeded-up robust features and fisher vector encoding
15. Komulainen, J., Hadid, A., and Pietikäinen, M. (October, January 29). Context based face anti-spoofing. Proceedings of the BTAS, Arlington, VA, USA.
16. Pan, G., Sun, L., Wu, Z., and Lao, S. (2007, January 18–23). Eyeblink-based anti-spoofing in face recognition from a generic webcamera. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA.10.1109/ICCV.2007.4409068 ↗
17. Liveness detection for embedded face recognition system
18. Li, J.W. (2008, January 12–15). Eye blink detection based on multiple gabor response waves. Proceedings of the ICMLC, Kunming, China.
19. Ali, A., Deravi, F., and Hoque, S. (2012, January 25–29). Liveness detection using gaze collinearity. Proceedings of the ICEST, Houston, TX, USA.10.1109/EST.2012.12 ↗
20. Li, X., Komulainen, J., Zhao, G., Yuen, P.C., and Pietikäinen, M. (2016, January 4–8). Generalized face anti-spoofing by detecting pulse from face videos. Proceedings of the ICPR, Cancun, Mexico.
21. Liu, Y., Jourabloo, A., and Liu, X. (2018, January 18–22). Learning deep models for face anti-spoofing: Binary or auxiliary supervision. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00048 ↗
22. Lin, B., Li, X., Yu, Z., and Zhao, G. (2019, January 29–31). Face liveness detection by rppg features and contextual patch-based cnn. Proceedings of the ICBEA, Stockholm, Sweden.10.1145/3345336.3345345 ↗
23. Yu, Z., Peng, W., Li, X., Hong, X., and Zhao, G. (November, January 27). Remote heart rate measurement from highly compressed facial videos: An end-to-end deep learning solution with video enhancement. Proceedings of the ICCV, Seoul, Republic of Korea.
24. Face spoofing detection using colour texture analysis10.1109/TIFS.2016.2555286 ↗
25. Spoofing detection on facial images recognition using LBP and GLCM combination10.1088/1742-6596/971/1/012014 ↗
26. Attention-Based Two-Stream Convolutional Networks for Face Spoofing Detection10.1109/TIFS.2019.2922241 ↗
27. Rajeswaran, S., and Kumar, S. (2019, January 25–26). Face-Spoof detection system using convolutional neural network. Proceedings of the International Conference on Recent trends in Electronics, Computing and Communication Engineering (ICRTECC), Chennai, India.
28. Hashemifard, S., and Akbari, M. (2021). A Compact Deep Learning Model for Face Spoofing Detection. arXiv.
29. Online Attendance System Using Face Recognition
30. Face spoofing detection based on multi-scale color inversion dual-stream convolutional neural network10.1016/j.eswa.2023.119988 ↗
31. Face spoofing detection using Heterogeneous Auto-Similarities of Characteristics10.1016/j.engappai.2023.107788 ↗
32. Robust face anti-spoofing with Dual Probabilistic Modeling10.1016/j.patcog.2025.111700 ↗
33. Channel difference transformer for face anti-spoofing10.1016/j.ins.2025.121904 ↗
34. Unmasking Deception: A Comprehensive Survey on the Evolution of Face Anti-spoofing Methods10.1016/j.neucom.2024.128992 ↗
35. Face (2025, February 18). Spoofing Dataset. Available online: https://universe.roboflow.com/face-hgc6e/spoofing-wqkzq.
36. Ma, X., Geng, Z., and Bie, Z. (2021, July 21). Depth Estimation from Single Image Using CNN-Residual Network. Semantic Scholar. Available online: https://cs231n.stanford.edu/reports/2017/pdfs/203.pdf.
37. Pandey, A. (2025, July 08). Face Liveness Detection Using Depth Map Prediction. Available online: https://github.com/anand498/Face-Liveness-Detection.
38. Xiao, J., Wang, W., Zhang, L., and Liu, H. (2024). A MobileFaceNet-Based Face Anti-Spoofing Algorithm for Low-Quality Images. Electronics, 13.10.3390/electronics13142801 ↗
39. Quy, N.D. (2025, July 08). Face Anti-Spoofing Using MobileNet. Available online: https://github.com/dinhquy94/face-antispoofing-using-mobileNet.
40. Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A ConvNet for the 2020s. arXiv.10.1109/CVPR52688.2022.01167 ↗
41. Tan, M., and Le, Q.V. (2021). EfficientNetV2: Smaller Models and Faster Training. arXiv.
42. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale. arXiv.
43. Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., and Dong, L. (2022, January 18–24). Swin Transformer V2: Scaling Up Capacity and Resolution. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01170 ↗
44. Belli, D., Das, D., Major, B., and Porikli, F. (2022, January 4–8). A Personalized Benchmark for Face Anti-spoofing. Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Waikoloa, HI, USA.10.1109/WACVW54805.2022.00040 ↗
45. Doubango AI (2025, July 08). Doubango AI 3D Passive Face Liveness Detection. Available online: https://github.com/DoubangoTelecom/FaceLivenessDetection-SDK.