Performance Comparison of Classification Algorithms for Face Anti-Spoofing using Codebook Features
Keywords:
Biometrics Authentication, Face Anti-Spoofing, LBG algorithm, KEVR algorithm, Machine Learning (ML) Algorithms, Presentation Attack DetectionAbstract
Face recognition systems are prone to break by using face images and video or mask methods, termed face spoofing attacks. The 2D attacks include fake photo attacks, warped photos, video display attacks, and 3D attacks performed using 3D masks. Detection of attacks with higher efficiency remains a problem due to factors such as illumination and dataset variations. The paper focuses on designing a system to detect 3D mask attacks with higher efficiency and lower error rate. The proposed system consists of use of codebook features obtained using Linde-Buzo-Gray (LBG) Algorithm and Kekre’s Error Vector Rotation (KEVR) algorithms for different sizes from 8 to 256. The results are obtained for various Machine Learning(ML) classifiers and evaluated using Attack Presentation Classification Error Rate (APCER), Half Total Error Rate (HTER) and Bonafide Presentation Classification Error Rate (BPCER) for both Algorithms on 3D MAD Dataset. The KNN variants perform well for KEVR features, and SVM with Logistic Regression has higher results for LBG features. The analysis indicates the proposed method’s improved performance over the existing methods of face anti-spoofing.
References
S. Bhattacharjee and S. Marcel, “What you can’t see can help you - extended- range imaging for 3d-mask presentation attack detection,” in 2017 International Conference of the Biometrics Special Interest Group (BIOSIG). IEEE, 2017, pp. 1–7.
D. Wen, H. Han, and A. K. Jain, “Face spoof detection with image distortion analysis,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 4, p. 746—761, 2015.
N. Erdogmus and S. Marcel, “Spoofing face recognition with 3d masks,” IEEE Transactions on Information Forensics and Security, vol. 9, no. 7, pp. 1084–1097, jul 2014.
T. Edmunds and A. Caplier, “Motion-based countermeasure against photo and video spoofing attacks in face recognition,” Journal of Visual Communication and Image Representation, vol. 50, no. 1, pp. 314–332, jan 2018.
N. Daniel and A. Anitha, “Texture and quality analysis for face spoofing detection,” Computers Electrical Engineering, vol. 94, no. 6, p. 107293, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0045790621002731
D. Menotti, G. Chiachia, A. Pinto, W. R. Schwartz, H. Pedrini, A. X. Falcao, and A. Rocha, “Deep representations for iris, face, and fingerprint spoofing detection,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 4, pp. 864– 879, apr 2015.
Z. Boulkenafet, J. Komulainen, and A. Hadid, “On the generalization of color texture-based face anti-spoofing,” Image and Vision Computing, vol. 77, no. 9, pp. 1–9, 2018.
Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face spoofing detection using colour texture analysis,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 8, pp. 1818–1830, aug 2016.
Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, and S. Z. Li, “A face antispoofing database with diverse attacks,” in 2012 5th IAPR international conference on Biometrics (ICB). IEEE, 2012, pp. 26–31.
N. Erdogmus and S. Marcel, “Spoofing in 2d face recognition with 3d masks and anti-spoofing with kinect,” in 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS). IEEE, 2013, pp. 1–6.
S. P. S. H. B. Kekre, S. D. Thepade and S. Shinde, “Devnagari handwritten character recognition using lbg vector quantization with gradient masks,” in 2013 International Conference on Advances in Technology and Engineering (ICATE), 2013, pp. 1–4.
B. Mirzaei, H. Nezamabadi-pour, and D. Abbasi-moghadam, “An effective codebook initialization technique for lbg algorithm using subtractive clustering,” in 2014 Iranian Conference on Intelligent Systems (ICIS), 2014, pp. 1–5.
S. T. K. T. S. D. Kekre, H. B. and S. Sanas, “Image retrieval using texture features extracted as vector quantization codebooks generated using lbg and kekre error vector rotation algorithm,” in Technology Systems and Management, K. Shah, V. R. Lakshmi Gorty, and A. Phirke, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp. 207–213.
R. Raghavendra and C. Busch, “Novel presentation attack detection algorithm for face recognition system: Application to 3d face mask attack,” in 2014 IEEE International Conference on Image Processing (ICIP). IEEE, oct 2014, pp. 323–327.
A. Pinto, H. Pedrini, W. R. Schwartz, and A. Rocha, “Face spoofing detection through visual codebooks of spectral temporal cubes,” IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 4726–4740, 2015.
R. S. F. S Naveen and R. S. Moni, “Face recognition and authentication using lbp and bsif mask detection and elimination,” in 2016 International Conference on Communication Systems and Networks (ComNet). IEEE, 2016, pp. 103–106.
P. P. Chan, W. Liu, D. Chen, D. S. Yeung, F. Zhang, X. Wang, and C.-C. Hsu, “Face liveness detection using a flash against 2d spoofing attack,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 2, pp. 521–534, 2017.
Y. Ma, L. Wu, Z. Li et al., “A novel face presentation attack detection scheme based on multi-regional convolutional neural networks,” Pattern Recognition Letters, vol. 131, no. 3, pp. 261–267, 2020.
D. Mu and T. Li, “Face anti-spoofing with multi-color double-stream cnn,” in Proceedings of the 13th International Conference on Distributed Smart Cameras, 2019, pp. 1–4.
S. Kumar, S. Rani, A. Jain, C. Verma, M. S. Raboaca, Z. Illes, and B. C. Neagu, “Face spoofing, age, gender and facial expression recognition using advance neural network architecture-based biometric system,” Sensors, vol. 22, no. 14, p. 5160, 2022.
Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, and S. Z. Li, “A face antispoofing database with diverse attacks,” in 2012 5th IAPR International Conference on Biometrics (ICB), 2012, pp. 26–31.
Y. H. M. B. V. K. Babita Sonare, Shambhavi Mokadam, “Face liveness detection using deep learning and support vector machine,” International Journal of Advanced Science and Technology, vol. 29, no. 12, pp. 2566–2572, 2020. [Online]. Available: http://sersc.org/Journals/index.php/IJAST/article/view/24737
G. D. Simanjuntak, K. Nur Ramadhani, and A. Arifianto, “Face spoofing detection using color distortion features and principal component analysis,” in 2019 7th International Conference on Information and Communication Technology (ICoICT), 2019, pp. 1–5.
S. Hemajothi, S. Abirami, and S. Aishwarya, “A novel colour texture based face spoofing detection using machine learning,” Acta Technica Corviniensis-Bulletin of Engineering, vol. 13, no. 2, pp. 47–52, 2020.
T. de Freitas Pereira, J. Komulainen, A. Anjos, J. M. De Martino, A. Hadid, M. Pietikainen, and S. Marcel, “Face liveness detection using dynamic texture,” EURASIP Journal on Image and Video Processing, vol. 2014, no. 1, pp. 1–15, 2014.
I. Chingovska, A. Anjos, and S. Marcel, Anti-spoofing: Evaluation Methodologies, Boston, MA, 2009, pp. 1–6.
A. Mahore and M. Tripathi, “Detection of 3d mask in 2d face recognition system using dwt and lbp,” in 2018 IEEE 3rd International Conference on Communication and Information Systems (ICCIS). IEEE, 2018, pp. 18–22.
R. Shao, X. Lan, and P. C. Yuen, “Joint discriminative learning of deep dynamic textures for 3d mask face anti-spoofing,” IEEE Transactions on Information Forensics and Security, vol. 14, no. 4, pp. 923–938, 2018.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
