An Efficient Velocity Estimation Approach for Face Liveness Detection using Sparse Optical Flow Technique

N Nanthini; N Puviarasan; P Aruna

doi:10.17485/IJST/v14i25.942

Article

An Efficient Velocity Estimation Approach for Face Liveness Detection using Sparse Optical Flow Technique

VIEWS 1440
PDF 419

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i25.942

Year: 2021, Volume: 14, Issue: 25, Pages: 2128-2136

Original Article

An Efficient Velocity Estimation Approach for Face Liveness Detection using Sparse Optical Flow Technique

N Nanthini ^{1, *}, N Puviarasan ², P Aruna ³

1 Research scholar, Department of CSE, Annamalai University, Chidambaram, India

2 Professor, Department of CIS, Annamalai University, Chidambaram, India

3 Professor, Department of CSE, Annamalai University, Chidambaram, India

*corresponding author email: [email protected]

Received Date:28 May 2021, Accepted Date:04 July 2021, Published Date:21 July 2021

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To propose a new liveness detection algorithm using optical flow to ensure the presence of actual live face into a photograph or 2D masks in face recognition biometric security systems. Methods: This work proposes an anti-spoofing model namely Sparse Optical Flow Technique with Velocity Estimation Approach (SOFT_VEA). Optical flow is an effective method for tracking objects in motion. It is adapted in this work to capture facial movements and decide the liveness state. The proposed algorithm considers real faces and two kinds of photo imposters. Findings: From the input video, the motion information of specific facial landmark points is captured by an optical flow algorithm. Then, the velocity of those landmark points is estimated via Euclidean distance. Based on this calculated velocity, the fake face is discriminated from the real face using a threshold value. The Empirical study shows that the proposed face liveness detection model is effective with an accuracy of 88% and Half Total Error Rate (HTER) of 2.45. Novelty: The proposed work is based on real face and photo imposters. The liveness detection algorithm is developed with a novel velocity estimation approach. It is very helpful for biometric security systems.

Keywords

Biometric security system, Liveness detection, Antispoofing, Facial landmarks, Optical flow, Euclidean distance

References

Hasan M, Mahmud SMH, Li XY. Face Anti-Spoofing Using Texture-Based Techniques and Filtering Methods. Journal of Physics-conference Series. 2019;p. 1–10. Available from: 10.1088/1742-6596/1229/1/012044
Bhele S, Mankar V. A Review Paper on Face Recognition Techniques. International journal of research in computer science engineering and technology. 2012;1:2278–2311.
Parmar D, Mehta B. Face Recognition methods and applications. International Journal of Computer Technology Applications. 2013;4:84–86. Available from: https://arxiv.org/abs/1403.0485
Kollreider K, Fronthaler H, Faraj MI, Bigun J. Real-Time Face Detection and Motion Analysis With Application in “Liveness” Assessment. IEEE Transactions on Information Forensics and Security. 2007;2(3):548–558. Available from: https://dx.doi.org/10.1109/tifs.2007.902037
Shin J, Kim S, Kang S, Lee SW, Paik J, Besmaabidi. MongiAbidi Optical flow-based real-time object tracking using non-prior training active feature mode. Real-Time Imaging. 2005;11:204–218. Available from: 10.1016/j.rti.2005.03.006
Kollreider K, Fronthaler H, Bigun J. Evaluating liveness by face images and the structure tensor. In: Proceedings of 4th IEEE Workshop on Automatic Identification Advanced Technologies AutoID. (pp. 75-80) 2005. 10.1109/AUTOID.2005.20
Ahmad R, Naghsh-Nilchi, Roshanzamir M. An Efficient Algorithm for Motion Detection based Facial Expression Recognition using Optical Flow. 2006;14:318–323. Available from: https//doi.org/10.5281/zenodo.1063056
Kollreider K, Fronthaler H, Bigun J. Non-intrusive liveness detection by face images. Image and Vision Computing. 2009;27(3):233–244. Available from: https://dx.doi.org/10.1016/j.imavis.2007.05.004
Bao W, Li H, Li N, Jiang W. A liveness detection method for face recognition based on optical flow field. proceedings of International Conference on Image Analysis and Signal Processing. 2009;p. 233–236. Available from: 10.1109/IASP.2009.5054589
Fujita K, Hanada T, Kitazawa Y, Kawabe A. A debris image tracking using optical flow algorithm. Advances in Space Research. 2012;49(5):1007–1018. Available from: https://dx.doi.org/10.1016/j.asr.2011.12.010
Singh AK, Joshi P, Nandi GC. Face Recognition with Liveness Detection using Eye and Mouth Movement. In: Proceeding of International Conference on Signal Propagation and Computer Technology (ICSPCT). (pp. 592-597) 2014. 10.1109/ICSPCT.2014.6884911
Singh M, Arora AS. A robust anti-spoofing technique for face liveness detection with morphological operations. Optik. 2017;139:347–354. Available from: https://dx.doi.org/10.1016/j.ijleo.2017.04.004
Feng L, Po LM, Li Y, Xu X, Yuan F, Cheung TCH, et al. Integration of image quality and motion cues for face anti-spoofing: A neural network approach. Journal of Visual Communication and Image Representation. 2016;38:451–460. Available from: https://dx.doi.org/10.1016/j.jvcir.2016.03.019
S. K, S. V. Contour-based object tracking in video scenes through optical flow and gabor features. Optik. 2018;157:787–797. Available from: https://dx.doi.org/10.1016/j.ijleo.2017.11.181
Pragadeeswari CK, Yamuna G, Beham GY. Optical flow detection and tracking of gauzes and cancer cells. Materials Today: Proceedings. 2020;33:3558–3563. Available from: https://dx.doi.org/10.1016/j.matpr.2020.05.525
Parveen S, Ahmad SM, Abbas NH, Adnan WA, Hanafi M, Naeem N. Face liveness detection using dynamic local ternary pattern (DLTP) First Computing. 2016;5(2). Available from: https://doi.org/10.3390/computers5020010

Copyright

© 2021 Nanthini et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)