Face Spoofing Detection from a Single Image using Diffusion Speed Model
Keywords:
Total Variation, SVM, LSP, Additive Operation Splitting, LSP, NUAAAbstract
Face spoofing using photographs is one of the most well-known strategies of attacking face recognition and verification frameworks. This paper proposes a spoofing detection method based on the diffusion speed of the input image. The diffusion speed is nothing but the difference of pixel value between original image and diffused image. The implementing method is based on the diffusion speed, and there is no user involvement, and works with a single input image. Diffusion speed is calculated by using total variation (TV) method, and to solve the nonlinear scalar valued equation additive operator (AOS) algorithm is applied. The local speed patterns are calculated from diffused speed image at each pixel position. And these pattern are input into the SVM classifier.
References
- J. Bai, T. Ng, X. Gao, and Y. Shi, "Is physics-basedliveness detection truly possible with a single image?”, IEEE International Symposium on Circuits and Systems, 2010, pp. 3425-3428.
- X. Tan, Y. Li, J. Liu, and L. Jiang, "Face liveness detection from a single image with sparse low rank bilinear discriminative model”, Computer Vision ECCV 2010, vol. 6316, pp. 504-517, 2010.
- J. Maatta, A. Hadid, and M. Pietikainen, "Face spoofing detection from single image using micro-textureanalysis,” International Joint Conference on Biometrics (IJCB), 2011.
- G. Pan, L. Sun, Z. Wu, and S. Lao, "Eye blink-based anti- Spoofing in face recognition from a generic web camera,” IEEE 11thInternational Conference on Computer Vision, 2007, pp. 1-8.
- G. Pan, Z. Wu, and L. Sun, "Liveness detection for face recognition,” Recent Advances in Face Recognition, December 2008, pp. 109-124.
- G. Pan, L. Sun, Z. Wu, and Y. Wang, "Monocularcamera-based face liveness detection by combining eyeblink and scene context” Journal of Telecommunication Systems, 2009.
- W. Bao, H. Li, N. Li, and W. Jiang, "A liveness detection method for face recognition based on optical flow field,” IEEE International Conference on Image Analysis and Signal Processing, 2009, pp. 233-236.
- K. Kollreider, H. Fronthaler, J. Bigun, "Non-intrusiveliveness detection by face images” Image and Vision Computing, 2009, vol. 27, no. 3, pp. 233-244.
- A. Anjos, M. M. Chakka, and S. Marcel, "Motion-basedcounter measures to photo attacks in face recognition” IET Biometrics, vol. 3, no. 3, pp. 147-158, September 2014.
- Santosh Tirunagari, Norman Poh, David Windridge, Aamo Iorliam, Nick Suki, Anthony T. S. Ho, "Detection of face spoofing using visual dynamics” IEEE Transaction on Information Forensics and Security”, vol. 10, No. 4, April 2015.
- Won Jun Kim, Sungjoo Suh, Jae Joon Han, "face liveness detection from single image via diffusion speed model” IEEE Transaction on Image Processing, vol. 24, No. 8, August 2015.
- R.Raghavendra, Kiran. B. Raju, Christoph Bush, "Presentation attack detection for face recognition using Light field camera", IEEE Transaction on Image Processing, vol. 24, No. 3, March 2015
- J. Ralli "PDE Based Image Di?usion and AOS”, PhD thesis, 2014.
- P. Perona and J. Malik, "Scale-space and edge dtection using anisotropic diffusion” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 629-639, July 1990.
- J. Weickert, B.M.T.H. Romeny, and M.A. Viergever, "Ef?cient and reliable schemes for nonlinear diffusion ?ltering” Transaction on Image Processing, vol. 7, no. 3, pp. 398-410, Mar. 1998.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST
This work is licensed under a Creative Commons Attribution 4.0 International License.
