生物驗證技術，是指利用身體特徵或行為特徵去達到驗證或辨識身分。生物驗證已經包含許多技術，像是指紋、臉部、虹膜、及語音驗證等等，其中指紋和虹膜驗證已經獲得相當高的準確率。雖然臉部驗證逐漸的普及，但仍然存在風險，其中是假臉問題。為了防止冒充者利用重新影印照片、人臉面具、或是在裝置上播放的影片進行欺騙，進而提出假臉偵測 (Face spoofing detection)。由於假臉的顏色、紋理、及質量特徵會不同於真臉，所以本論文對臉部區域的特徵進行預測，其中利用影像失真分析特徵 (Image Distortion Analysis features，簡稱IDA features) 包括模糊特徵 (Blurriness feature)、色度特徵 (Chromatic moment feature)、及顏色多樣性特徵 (Color diversity feature)。當額外裝置攻擊時，非臉部區域會受到裝置的邊框限制而影響，反而造成的更多背景變化；相反的，真臉不會有裝置邊框的問題。因此，本論文基於特徵提取的方式提出新的光流法特徵 (Optical Flow feature)。我們目的是對非臉部區域計算每一點像素位移變化，然後只計算明顯遭受到攻擊的四個區塊的位移，不僅能夠大幅降低光流法的計算量且能夠有效得提升假臉偵測的準確率。利用上述所提取的多特徵組合成特徵向量並透過支持向量機 (Support Vector Machine，簡稱SVM) 進行模型訓練，並透過分數級融合 (Score-level fusion)進行偵測真臉或假臉。最終結果分別顯示在CASIA數據庫和Replay-Attack數據庫，我們有效得的結合光流法特徵和影像失真分析特徵，並且有效提升5.23%及 3.58%的準確度，而且在沒有使用額外裝置下整個系統達到了每一偵的執行速度為0.081秒。

Biometric verifications are the ways to verify the identity of a subject with the use of physical features or behavioral features. There are many technologies of biometric verifications, such as fingerprint, face, iris, or speech verification, etc. Finger and iris verifications have achieved high accuracy. Although face verification is gradually becoming popular, there still have risks, such as the concern of spoofing face. Face spoofing detection can be used to prevent the imposters using a printed photo, a facial mask, or a replayed video on the screen to attack the face verification system. Since the color, texture, and quality features of the spoofing faces are different from genuine faces, this thesis utilized features of the face region to predict whether if the input face is genuine. The Image Distortion Analysis features (IDA features), including Blurriness feature, Chromatic feature and Color Diversity feature are used in the proposed system. When attacking by extra devices, the non-facial region is affected by limitations of boundaries, which will cause more changes to the background; on the contrary, the genuine faces do not have this problem. Therefore, this thesis proposed a new Optical Flow feature. The goal is to calculate the displacement of each pixel on the non-facial region. We only compute on the four blocks that are obviously affected by attacks, which can not only effectively reduce the calculation of the Optical flow, but also improve the face spoofing detection performance. Then, the Support Vector Machine (SVM) is used to train the model using the combined feature vectors. Last, score-level fusion is used to distinguish genuine or spoofing faces. The combined new Optical Flow feature and IDA features can effectively improve 5.23% and 3.58% accuracy on the CASIA Database and the Replay-Attack Database, respectively. Furthermore, without using addition hardware, the proposed system achieves the execution time of 0.081 sec. for each frame.

[1]
S. Modi, S. Elliott, J. Whetsone, and H. Kim, “Impact of age groups on fingerprint recognition performance,” in IEEE Workshop on Automatic Identification Advanced Technologies, pp. 19-23, June 2007.
[2]
R.P. Wildes, “Iris Recognition: An Emerging Biometric Technology”, Proceedings of the IEEE, vol. 85, no. 9, pp.1348-1363, Sept. 1997
[3]
M. A. Turk and A. P. Pentland, “Face Recognition Using Eigenfaces,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[4]
A. Anjos and S. Marcel, "Counter-measures to photo attacks in face recognition: a public database and a baseline," in 2011 International Joint Conference on Biometrics (IJCB), pp. 1-7, 2011.
[5]
X. Tan, Y. Li, J. Liu, and L. Jiang, “Face liveness detection from a single image with sparse low rank bilinear discriminative model,” in Proceedings of the 11th European Conference Computer Vision, pp. 504-517, 2010.
[6]
Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, and S. Z. Li, “A face antispoofing database with diverse attacks,” in Proceedings of 5th IAPR International Conference on Biometrics (ICB), pp. 26-31, Mar./Apr. 2012.
[7]
I. Chingovska, A. Anjos, and S. Marcel, “On the effectiveness of local Binary patterns in face anti-spoofing,” in Proceedings of International Conference of the Biometrics Special Interest Group (BIOSIG), pp. 1–7, Sep. 2012.
[8]
I. Manjani, S. Tariyal, M. Vatsa, R. Singh, and A. Majumdar, “Detecting silicone mask-based presentation attack via deep dictionary learning,” IEEE Transactions on Information Forensics Security, vol. 12, no. 7, pp. 1713-1723, Jul. 2017.
[9]
J. Galbally, S. Marcel, and J. Fierrez, “Image quality assessment for fake biometric detection: Application to iris, fingerprint, and face recognition,” IEEE Transactions on Image Processing, vol. 23, no. 2, pp. 710-724, Feb. 2014.
[10]
K. Kollreider, H. Fronthaler, M. I. Faraj, and J. Bigun, “Real-time face detection and motion analysis with application in ‘liveness’ assessment,” IEEE Transactions on Information Forensics Security, vol. 2, no. 3, pp. 548-558, Sep. 2007.
[11]
D. Wen, H. Han, and A. K. Jain, “Face spoof detection with image distortion analysis,” IEEE Transactions on Information Forensics Security, vol. 10, no. 4, pp. 746-761, Apr. 2015.
[12]
J. Määttä, A. Hadid, and M. Pietikäinen, “Face spoofing detection from single images using micro-texture analysis,” in Proc. IEEE International Joint Conference on Biometrics (IJCB), pp. 1-7, Oct. 2011.
[13]
Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face anti-spoofing based on color texture analysis,” in Proceeding of IEEE Internatoion Conference on Image Processing (ICIP), pp. 2636–2640, Sep. 2015.
[14]
A. Agarwal, R. Singh, and M. Vatsa, “Face anti-spoofing using Haralick features,” in Biometrics Theory, Applications and Systems (BTAS), 2016 IEEE 8th International Conference on, pp. 1-6. IEEE, 2016.
[15]
R. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems Man Cybernetics-Systems, vol. 3, no 6, pp. 610-621, Nov. 1973.
[16]
Z. Boulkenafet, J. Komulainen, X. Feng, and A. Hadid, “Scale space texture analysis for face anti-spoofing,” in Proceeding of International Conference on Biometrics (ICB), pp. 1-6, Jun. 2016.
[17]
E. H. Adelson, C. H. Anderson, J. R. Bergen, P. J. Burt, and J. M. Ogden, “Pyramid methods in image processing,” Radio Corporation of America (RCA) engineer, vol 29, no. 6, pp. 31-41, 1984.
[18]
P. P. K. 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 Security, vol. 13, no. 2, pp. 521-534, Feb. 2017
[19]
H. Steiner, A. Kolb, and N. Jung, “Reliable face antispoofing using multispectral SWIR imaging,” in 2016 International Conference on Biometrics (ICB), pp. 1-8, June 2016.
[20]
X. Tan and B. Triggs, “Enhanced local texture feature sets for face recognition under difficult lighting conditions,” IEEE Transactions on Image Processing, vol. 19, no. 6, pp. 1635-1650, June 2010.
[21]
W. Bao, H. Li, N. Li, and W. Jiang, “A liveness detection method for face recognition based on optical flow field,” in 2009 on Image Analysis and Signal Processing, pp. 233-236, IEEE, 2009.
[22]
G. Pan, L. Sun, Z. Wu, and S. Lao, “Eyeblink-based anti-spoofing in face recognition from a generic web camera,” in IEEE International Conference on Computer Vision, pp. 1-8, 2017.
[23]
S. Tirunagari, N. Poh, D. Windridge, A. Iorliam, N. Suki, and A. T. S. Ho, “Detection of face spoofing using visual dynamics,” in IEEE Transactions on Information Forensics Security, vol. 10, no. 4, pp. 762-777, Apr. 2015.
[24]
S. Bharadwaj, T. I. Dhamecha, M. Vatsa, and R. Singh, “Computationally efficient face spoofing detection with motion magnification,” in Proceeding of IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 105-110, Jun. 2013.
[25]
H.-Y. Wu, M. Rubinstein, E. Shih, J. V. Guttag, F. Durand, and W. T. Freeman, “Eulerian video magnification for revealing subtle changes in the world,” ACM Transactions on Graphics, vol. 31, no. 4, pp. 65, 2012.
[26]
H. Khalajzadeh, M. Mansouri and M. Teshnehlab, “Face Recognition using Convolutional Neural Network and Simple Logistic Classifier,” 2012 online conference on soft computing industrial applications, Dec. 2012.
[27]
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks, ” International Conference Neural information processing systems, 2012.
[28]
Y. Zhou, H. Chang, K. Barner, P. Spellman, and B. Parvin, “Classification of histology sections via multispectral convolutional sparse coding,” Internation Conference on Computer Vision and Pattern Recognition, pp. 3081-3088, 2014.
[29]
Y. Liu, A. Jourabloo, and X. Liu, “Learning deep models for face antispoofing: Binary or auxiliary supervision,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 389-398, Jun. 2018.
[30]
Z. Xu, S. Li, and W. Deng, “Learning temporal features using LSTM-CNN architecture for face anti-spoofing,” in 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 141–145. IEEE, 2015.
[31]
F. Gers, N. Schraudolph, and J. Schmidhuber, “Learning Precise Timing with LSTM Recurrent Networks,” Journal of Machine Learning Research, vol. 3, no.1 , pp. 115–143, 2002.
[32]
P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 511-518, 2001.
[33]
Open CV: http://opencv.org/, [Online].
[34]
F. Crete, T. Dolmiere, P. Ladret, and M. Nicolas, “The blur effect: Perception and estimation with a new no-reference perceptual blur metric,” in Proceedings of SPIE, San Jose, CA, USA, p. 64 920I, 2007.
[35]
Y. Chen, Z. Li, M. Li, and W.-Y. Ma, “Automatic classification of photographs and graphics,” in Proceedings of International Congress on Mathematical Education, pp. 973-976, Jul. 2006.
[36]
B. A. Rahman, N. Anwar, K. C. Wei and J. See, “RGB-h-CbCr Skin Color Model for Human Face Detection,” In MMU International Symposium on Information and Communications Technologies (M2USIC), Petaling Jaya, Malaysia, 2006.
[37]
M. Stricker, and M. Orengo, "Similarity of color images", in Proceedings of SPIE Storage and Retrieval for image and Video Databases Conference, pp. 381-392, 1995.
[38]
B. K. P. Horn and B. G. Schunck, “Determining Optical Flow,” in Artificial Intelligence, vol. 17, no. 1-3, pp. 185-203, 1981.
[39]
A. Anjos, M. M. Chakka, and S. Marcel, “Motion-based countermeasures to photo attacks in face recognition,” in IET Biometrics, vol. 3, no. 3, pp. 147-158, Sep. 2013.
[40]
G. Farnebäck, “Two-frame motion estimation based on polynomial expansion,” in Image Analysis, New York, NY, USA: Springer, vol. 2749, pp. 363-370, 2003.
[41]
V. Vielzeuf, S. Pateux, and F. Jurie, “Temporal multimodal fusion for video emotion classification in the wild,” in Proceedings of 19th ACM International Conference on Multimodal Interaction, pp. 569-576, 2017.
[42]
B. E. Boser, I. Guyon, and V. Vapnik, “A training algorithm for optimal margin classifiers,” in Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 144-152. ACM Press, 1992.
[43]
T.d.F. Pereira, J. Komulainen, A. Anjos, J.M. De Martino, A. Hadid, M. Pietikäinen, and S. Marcel, “Face liveness detection using dynamic texture,” EURASIP Journal on Image Video Processing, vol. 2014, no. 1, pp. 1-15, Dec. 2014.
[44]
L. B. Zhang, F. Peng, L. Qin, and M. Long, “Face spoofing detection based on color texture Markov feature and support vector machine recursive feature elimination,” Journal of Visual Communication and Image Representation, vol. 51, no.6 , pp. 56-69, Feb. 2018.
[45]
F. Peng, L. Qin, and M. Long, “Face presentation attack detection using guided scale texture,” in Multimedia Tools and Applications, vol. 77, no. 7, pp. 1-27, May 2017.
[46]
Y. Atoum, Y. Liu, A. Jourabloo, and X. Liu, “Face anti-spoofing using patch and depth-based CNNs,” in Proceedings of International Joint Conference on Biometrics, Denver, CO, USA, pp. 319-328, Oct. 2017.
[47]
X. Tu and Y. Fang, “Ultra-deep neural network for face anti-spoofing,” in Proceedings of International Conference on Neural Information Processing, pp. 686-695, 2017.
[48]
L. Li, X. Feng, Z. Boulkenafet, Z. Xia, M. Li, and A. Hadid, “An original face anti-spoofing approach using partial convolutional neural network,” in 2016 6th International Conference on Image Processing Theory Tools and Applications (IPTA), pp. 1-6. IEEE, 2016.
[49]
Y. A. U. Rehman, L. M. Po, and M. Liu, “LiveNet: Improving features generalization for face liveness detection using convolution neural networks,” Expert System Application, vol. 108, no 12, pp. 159-169, 2018
[50]
H. Chen, G. Hu, Z. Lei, Y. Chen, N. M. Robertson, and S. Z. Li, “Attention-Based Two-Stream Convolutional Networks for Face Spoofing Detection,” IEEE Transactions on Information Forensics and Security, pp. 578-593, 2019
[51]
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.
[52]
L. Li, X. Feng, Z. Xia, X. Jiang, and A. Hadid, “Face spoofing detection with local binary pattern network,” Journal of Visual Communication and Image Representation, vol. 54, no. 15, pp. 182-192, 2018.
[53]
X. Song, X. Zhao, L. Fang, and T. Lin, “Discriminative representation combinations for accurate face spoofing detection,” Pattern Recognition, vol. 85, no. 19, pp. 220-231, 2019.
[54]
H. Li, P. He, S. Wang, A. Rocha, X. Jiang, and A. C. Kot, “Learning generalized deep feature representation for face anti-spoofing,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 10, pp. 2639-2652, Oct 2018.