Face Anti-Spoofing Security: A Fusion of FaceNet and Blink Detection

Ryan Reynickha Fatullah; I Gede Susrama Mas Diyasa; Achmad Junaidi

doi:10.56480/jln.v5i3.1592

Authors

Ryan Reynickha Fatullah Universitas Pembangunan Nasional "Veteran" Jawa Timur
I Gede Susrama Mas Diyasa Universitas Pembangunan Nasional “Veteran” Jawa Timur
Achmad Junaidi Universitas Pembangunan Nasional “Veteran” Jawa Timur

DOI:

https://doi.org/10.56480/jln.v5i3.1592

Abstract View:

40

PDF downloads:

37

Keywords:

FaceNet, Dlib, MTCNN, SVM, OpenCV

Abstract

This research aims to develop a face recognition system that can distinguish between real and fake faces, using FaceNet for face recognition, Support Vector Machine (SVM) for model building, and Dlib for eye blink detection as an anti-spoofing method. The system is designed to enhance security in identity verification applications, such as online exams. In this study, face images taken from 15 student identities were tested to identify the system's ability to recognize real and fake faces. The test results show that FaceNet successfully recognizes recognized faces with high probability, while Dlib is effective in detecting eye blinks used to distinguish real faces from potential spoofing. The system distinguishes unrecognized faces with low probability and detects fake faces through static Eye Aspect Ratio (EAR) values, demonstrating the ability to detect spoofing. The overall accuracy of the system reached 97%, although some improvements are still needed, especially for extreme lighting conditions and face positions. This research shows great potential in the use of face recognition and blink detection technologies to enhance security in online identity verification applications.

References

Afifudin, M., Junaedi, A., Nugroho, A., Fithriyah, I., Pembangunan, U., Veteran, N., Timur, J., & Anyar, G. (2024). GWO-SVM : An Approach To Improving Svm Performance Using Grey Wolf Optimizer In Intellectual Disability Classification. 12(3), 4440–4453. https://doi.org/10.23960/jitet.v12i3S1.5359

Akhdan, S. R., Supriyanti, R., & Nugroho, A. S. (2023). Face recognition with anti spoofing eye blink detection. AIP Conference Proceedings, 2482(February). https://doi.org/10.1063/5.0113512

Ganidisastra, A. H. S., & Bandung, Y. (2021). An Incremental Training on Deep Learning Face Recognition for M-Learning Online Exam Proctoring. Proceedings - 2021 IEEE Asia Pacific Conference on Wireless and Mobile, APWiMob 2021, 213–219. https://doi.org/10.1109/APWiMob51111.2021.9435232

Hernandez-Ortega, J., Galbally, J., Fierrez, J., Haraksim, R., & Beslay, L. (2019). FaceQnet: Quality Assessment for Face Recognition based on Deep Learning. 2019 International Conference on Biometrics, ICB 2019. https://doi.org/10.1109/ICB45273.2019.8987255

Lancaster, T., & Cotarlan, C. (2021). Contract cheating by STEM students through a file sharing website: a Covid-19 pandemic perspective. International Journal for Educational Integrity, 17(1), 1–17. https://doi.org/10.1007/s40979-021-00070-0

Li, H. (2024). The application and challenges of different face recognition technologies in the three major fields of security , social media , and medical care. 0, 174–181. https://doi.org/10.54254/2755-2721/95/2024CH0051

Li, X., Luo, J., Duan, C., Zhi, Y., & Yin, P. (2021). Real-time detection of fatigue driving based on face recognition. IOP Conference Series: Earth and Environmental Science, 1802(2). https://doi.org/10.1088/1742-6596/1802/2/022044

Pramadi, A., Pali, M., Hanurawan, F., & Atmoko, A. (2017). Academic Cheating in School: A Process of Dissonance Between Knowledge and Conduct. Mediterranean Journal of Social Sciences, 8(6), 155–162. https://doi.org/10.1515/mjss-2017-0052

Purnomo, D. (2017). Model Prototyping Model Prototyping Pada Pengembangan Sistem Informasi. JIMP-Jurnal Informatika Merdeka Pasuruan, 2(2), 54–61. https://doi.org/10.37438/jimp.v2i2.67

Qi, S., Zuo, X., Feng, W., & Naveen, I. G. (2022). Face Recognition Model Based on MTCNN and Facenet. 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications, ICMNWC 2022, 1–5. https://doi.org/10.1109/ICMNWC56175.2022.10031806

Ryando, C., Sigit, R., & Dewantara, B. S. B. (2023). Comparison of Machine Learning Algorithms for Face Classification Using FaceNet Embeddings. Indonesian Journal of Computer Science, 12(2), 284–301. http://ijcs.stmikindonesia.ac.id/ijcs/index.php/ijcs/article/view/3135

Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07-12-June, 815–823. https://doi.org/10.1109/CVPR.2015.7298682

Singh, A. K., Krishna, S., & Poongodi, T. (2024). Face Recognition System Using Haar Cascade and LBP Classifier. Proceedings of International Conference on Communication, Computer Sciences and Engineering, IC3SE 2024, 99–104. https://doi.org/10.1109/IC3SE62002.2024.10593491

Susrama, I. G., Diyasa, M., Arman, D., Ayu, H., & Kuswardhani, C. (2024). Detection of Abnormal Human Sperm Morphology Using Support Vector Machine ( SVM ) Classification. 2(2), 57–63. https://doi.org/10.33005/itij.v2i2.36

Susrama, I. G., Diyasa, M., Putra, A. H., Rafka, M., & Ariefwan, M. (2022). Feature Extraction for Face Recognition Using Haar Cascade Classifier. 2022, 197–206. https://doi.org/10.11594/nstp.2022.2432

William, I., Ignatius Moses Setiadi, D. R., Rachmawanto, E. H., Santoso, H. A., & Sari, C. A. (2019). Face Recognition using FaceNet (Survey, Performance Test, and Comparison). Proceedings of 2019 4th International Conference on Informatics and Computing, ICIC 2019. https://doi.org/10.1109/ICIC47613.2019.8985786

Yu, Z., Zhao, C., Wang, Z., Qin, Y., Su, Z., Li, X., Zhou, F., & Zhao, G. (2020). Searching central difference convolutional networks for face anti-spoofing. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 5294–5304. https://doi.org/10.1109/CVPR42600.2020.00534