×

Face liveness detection scheme with static and dynamic featuress. (English) Zbl 1404.94019

Summary: Face liveness detection is a significant research topic in face-based online authentication. The current face liveness detection approaches utilize either static or dynamic features, but not both. In fact, the dynamic and static features have different advantages in face liveness detection. In this paper, we propose a scheme combining dynamic and static features to capture merits of them for face liveness detection. First, the dynamic maps are captured from the inter-frame motion in the video, which investigates motion information of the face in the video. Then, with a Convolutional Neural Network (CNN), the dynamic and static features are extracted from the dynamic maps and the frame images, respectively. Next, in CNN, the fully connected layers containing the dynamic and static features are concatenated to form a fused feature. Finally, the fused features are used to train a binary Support Vector Machine (SVM) classifier, which classifies the frames into two categories, i.e. frame with real or fake face. Experimental results and the corresponding analysis demonstrate that the proposed scheme is capable of discovering face liveness by fusing dynamic and static features and it outperforms the current state-of-the-art face liveness detection approaches.

MSC:

94A13 Detection theory in information and communication theory
68T05 Learning and adaptive systems in artificial intelligence
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Anjos, A., Chakka, M. M. and Marcel, S., Motion-based counter-measures to photo attacks in face recognition, Iet Biometr.3(3) (2014) 147-158.
[2] Bharadwaj, S., Dhamecha, T. I., Vatsa, M. and Singh, R., Computationally efficient face spoofing detection with motion magnification, IEEE. Conf. Computer Vision and Pattern Recognition13(4) (2013) 105-110.
[3] Bouguet, J. Y., Pyramidal implementation of the lucas kanade feature tracker description of the algorithm, Opencv Doc.22(2) (2000) 363-381.
[4] Chingovska, I., Anjos, A. and Marcel, S., On the effectiveness of local binary patterns in face anti-spoofing, Biometrics Special Interest Group, 2012, pp. 1-7.
[5] Erdogmus, N. and Marcel, S., Spoofing face recognition with 3d masks, IEEE Trans. Inf. Forens. Sec.9(7) (2014) 1084-1097.
[6] K. B. Housam, S. H. Lau, Y. H. Pang, Y. P. Liew and M. L. Chiang, Face spoofing detection based on improved local graph structure (2014).
[7] Jee, H. K., Jung, S. U. and Yoo, J. H., Liveness detection for embedded face recognition system, Enformatika1 (2006) 235-238.
[8] Kim, S., Yu, S., Kim, K. and Ban, Y., Face liveness detection using variable focusing, International Conference on Biometrics, 2013, pp. 1-6.
[9] Komulainen, J., Hadid, A. and Pietikinen, M., Face spoofing detection using dynamic texture, International Conference on Computer Vision, 2012, pp. 146-157.
[10] Maatta, J., Hadid, A. and Pietikainen, M., Face spoofing detection from single images using texture and local shape analysis, Iet Biometrics1(1) (2012) 3-10.
[11] Maatta, J., Hadid, A. and Pietikainen, M., Face spoofing detection from single images using micro-texture analysis, Int. Joint Conf. Biometrics, 2011, pp. 1-7.
[12] Menotti, D., Chiachia, G., Pinto, A. and Schwartz, W. Robson, Deep representations for iris, face, and fingerprint spoofing detection, IEEE Trans. Inf. Forens. Secur.10(4) (2014) 864-879.
[13] Pan, G., Sun, L., Wu, Z. and Lao, S., Eyeblink-based anti-spoofing in face recognition from a generic webcamera, IEEE Int. Conf. Computer Vision, ICCV 2007, Rio De Janeiro, Brazil, , October, 2007, pp. 1-8.
[14] Patel, K., Han, H. and Jain, A. K., Secure face unlock: Spoof detection on smartphones, IEEE Trans. Inf. Forens. Sec.11(10) (2016) 2268-2283.
[15] Pereira, T. D. F., Anjos, A., Martino, J. M. D. and Marcel, S., Can face anti-spoofing countermeasures work in a real world scenario?Int. Conf. Biometr., 2013, pp. 1-8.
[16] Pereira, T. D. F., Komulainen, J., Anjos, A., Martino, J. M. D., Hadid, A., Pietikinen, M. and Marcel, S., Face liveness detection using dynamic texture, Eurasip J. Image Video Process.2014(1) (2014), p. 2.
[17] Phan, Q. T., Dang-Nguyen, D. T., Boato, G. and Natale, F. G. B. D., Face spoofing detection using ldp-top, IEEE Int. Conf. Image Process., 2016, pp. 404-408.
[18] Schwartz, W. R., Rocha, A. and Pedrini, H., Face spoofing detection through partial least squares and low-level descriptors, Int. Joint Conf. Biometr., 2011, pp. 1-8.
[19] Siddiqui, T. A., Bharadwaj, S., Dhamecha, T. I., Agarwal, A., Vatsa, M., Singh, R. and Ratha, N., Face anti-spoofing with multifeature videolet aggregation, Int. Conf. Pattern Recognit., 2016, pp. 1035-1040.
[20] Sun, Y., Wang, X. and Tang, X., Deep learning face representation by joint identification-verification, Proc. Computer Vision and Pattern Recognition27 (2014) 1988-1996.
[21] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z., Rethinking the inception architecture for computer vision, Comput. Sci. (2015) 2818-2826.
[22] Tan, X., Li, Y., Liu, J. and Jiang, L., Face liveness detection from a single image with sparse low rank bilinear discriminative model, European Conf. Comput. Vision, 2010, pp. 504-517.
[23] Tirunagari, S., Poh, N., Windridge, D. and Iorliam, A., Detection of face spoofing using visual dynamics, IEEE Trans. Inf. Forens. Sec.10(4) (2015) 762-777.
[24] Wu, L., Xu, X., Cao, Y., Hou, Y. and Qi, W., Live Face Detection by Combining the Fourier Statistics and LBP (Springer International Publishing, 2014).
[25] Wu, L., Xu, Y., Xu, X., Qi, W. and Jian, M., A Face Liveness Detection Scheme to Combining Static and Dynamic Features (Springer International Publishing, 2016).
[26] Yan, J., Zhang, Z., Lei, Z. and Yi, D., Face liveness detection by exploring multiple scenic clues, Int. Conf. Control Automat. Robot. Vision, 2012, pp. 188-193.
[27] Zhang, Z., Yan, J., Liu, S. and Lei, Z., A face antispoofing database with diverse attacks, IAPR Int. Conf. Biometrics, 2012, pp. 26-31.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.