access icon free Face spoofing detection using a light field imaging framework

Face recognition systems are becoming ubiquitous, but they are vulnerable to spoofing attacks. The recently available light field cameras can be used for spoofing attack detection. In this study, the IST Lenslet Light Field Face Spoofing Database (IST LLFFSD) is proposed, consisting of 100 genuine images, from 50 subjects, captured with a Lytro ILLUM lenslet light field camera, and a set of 600 face spoofing attack images, captured using the same camera. The IST LLFFSD simulates six different types of presentation attacks, including printed paper, wrapped printed paper, laptop, tablet and two different mobile phones. This study also proposes a novel spoofing attack detection solution, based on a compact, yet effective, descriptor exploiting the colour and texture variations associated with the different directions of light captured in light field images. Extensive experiments show very effective results, with the proposed solution performing better than state-of-the-art alternatives for the face spoofing attack types considered.

Inspec keywords: image colour analysis; image texture; visual databases; face recognition

Other keywords: mobile phones; colour variations; wrapped printed paper; laptop; tablet; Lytro ILLUM lenslet light field camera; face recognition systems; texture variations; IST lenslet light field face spoofing database; IST LLFFSD; face spoofing attack images; spoofing attack detection solution; light-field imaging framework; face spoofing detection

Subjects: Computer vision and image processing techniques; Spatial and pictorial databases; Image recognition

References

    1. 1)
      • 33. Chang, C., Lin, C.: ‘LIBSVM – a library for support vector machines’, National Taiwan University. Available at: https://www.csie.ntu.edu.tw/~cjlin/libsvm/ [Accessed April 2017].
    2. 2)
      • 2. Ramachandra, R., Busch, C.: ‘Presentation attack detection methods for face recognition systems: a comprehensive survey’, ACM Comput. Surv., 2017, 50, (1), pp. 801837.
    3. 3)
      • 24. Patel, K., Han, H., Jain, A.: ‘Secure face unlock: spoof detection on smartphones’, IEEE TIFS, 2016, 11, (10), pp. 22682283.
    4. 4)
      • 10. Raghavendra, R., Raja, K., Busch, C., et al: ‘Exploring the usefulness of light field cameras for biometrics: an empirical study on face and iris recognition’, IEEE TIFS, 2016, 11, (5), pp. 922936.
    5. 5)
      • 35. ISO/IEC JTC1 SC37 Biometrics: ‘Information technology – presentation attack detection – Part 3: testing, reporting and classification of attacks’, ISO.ORG, 2016. Available at: https://www.iso.org/committee/313770/x/catalogue/ [Accessed April 2017].
    6. 6)
      • 34. Sepas-Moghaddam, A., Chiesa, V., Correia, P., et al: ‘The IST-EURECOM light field face database’. IWBF, Coventry, UK, April 2017.
    7. 7)
      • 12. Raghavendra, R., Raja, K., Yang, B., et al: ‘Multi-face recognition at a distance using light field camera’. IEEE IIH-MSP, Beijing, China, October 2013.
    8. 8)
      • 32. Dansereau, D.: ‘Light field toolbox v. 0.4’, 2016. Available at: http://www.mathworks.com/matlabcentral/fileexchange/49683-light field-toolbox-v0-4 [Accessed April 2017].
    9. 9)
      • 22. Zhang, Z., Yan, J., Liu, S., et al: ‘A face antispoofing database with diverse attacks’. IAPR ICB, Dehli, India, April 2012.
    10. 10)
      • 19. Tan, X., Li, Y., Liu, J., et al: ‘Face liveness detection from a single image with sparse low rank bilinear discriminative model’. ECCV, Crete, Greece, September 2010.
    11. 11)
      • 11. Raghavendra, R., Yang, B., Raja, K., et al: ‘A new perspective – face recognition with light field camera’. IEEE ICB, Madrid, Spain, June 2013.
    12. 12)
      • 14. Sepas-Moghaddam, A., Correia, P., Pereira, F., et al: ‘Light field local binary patterns description for face recognition’. IEEE ICIP, Beijing, China, September 2017.
    13. 13)
      • 21. Chingovska, I., Anjos, A., Marcel, S., et al: ‘On the effectiveness of local binary patterns in face anti-spoofing’. BIOSIG, Darmstadt, Germany, September 2012.
    14. 14)
      • 3. Hadid, A.: ‘Face biometrics under spoofing attacks: vulnerabilities, countermeasures, open issues, and research directions’. IEEE CVPRW, Columbus, OH, USA, June 2014.
    15. 15)
      • 7. Chingovska, I., Erdogmus, N., Anjos, A., et al: ‘Face recognition systems under spoofing attacks’. Face Recognition Across the Imaging Spectrum, NY, USA, February 2016, pp. 165194.
    16. 16)
      • 13. Raghavendra, R., Raja, K., Yang, B., et al: ‘Evaluation of super-resolution techniques for multi-face recognition using light field camera’. IEEE DSP, Santorini, Greece, July 2013.
    17. 17)
      • 29. Boulkenafet, Z., Komulainen, J., Hadid, A., et al: ‘Face spoofing detection using colour texture analysis’, IEEE TIFS, 2016, 11, (8), pp. 18181830.
    18. 18)
      • 8. Levoy, M., Hanrahan, P.: ‘Light field rendering’. SIGGRAPH, New York, NY, USA, August 1996.
    19. 19)
      • 26. Määttä, J., Hadid, A., Pietikäinen, M., et al: ‘Face spoofing detection from single images using micro-texture analysis’. IJCB, Washington, DC, USA, October 2011.
    20. 20)
      • 28. Hadid, A., Evans, N., Marcel, S., et al: ‘Biometrics systems under spoofing attack: an evaluation methodology and lessons learned’, IEEE SPM, 2015, 32, (5), pp. 2030.
    21. 21)
      • 5. Erdogmus, N., Marcel, S.: ‘Spoofing face recognition with 3D masks’, IEEE TIFS, 2014, 9, (7), pp. 10841097.
    22. 22)
      • 17. Kim, S., Ban, Y., Lee, S., et al: ‘Face liveness detection using a light field camera’, Sensors, 2014, 14, (12), pp. 7199.
    23. 23)
      • 15. Ji, Z., Zhu, H., Wang, Q., et al: ‘LFHOG: a discriminative descriptor for live face detection from light field image’. IEEE ICIP, Phoenix, AZ, USA, September 2016.
    24. 24)
      • 1. Galbally, J., Marcel, S., Fierrez, J., et al: ‘Biometric antispoofing methods: a survey in face recognition’, IEEE Access, 2014, 2, (1), pp. 15301552.
    25. 25)
      • 23. Wen, D., Han, H., Jain, A., et al: ‘Face spoof detection with image distortion analysis’, IEEE TIFS, 2015, 10, (4), pp. 746761.
    26. 26)
      • 18. Ojala, T., Pietikäinen, M., Harwood, D., et al: ‘A comparative study of texture measures with classification based on featured distributions’, Pattern Recognit., 1996, 29, (1), pp. 5159.
    27. 27)
      • 6. Yi, D., Lei, Z., Zhang, Z., et al: ‘Face anti-spoofing: multi-spectral approach’. Handbook of Biometric Anti-Spoofing, London, Springer-Verlag, July 2014, pp. 83102.
    28. 28)
      • 9. Ng, R.: ‘Digital light field photography’. PhD Thesis in Computer Engineering, Stanford University, California, USA, 2006.
    29. 29)
      • 16. Raghavendra, R., Raja, K., Busch, C., et al: ‘Presentation attack detection for face recognition using light field camera’, IEEE TIP, 2015, 24, (3), pp. 10601075.
    30. 30)
      • 20. Anjos, A., Marcel, S.: ‘Counter-measures to photo attacks in face recognition: a public database and a baseline’. IJCB, Washington, DC, USA, October 2011.
    31. 31)
      • 4. Erdogmus, N., Marcel, S.: ‘Spoofing in 2D face recognition with 3D masks and anti-spoofing with kinect’. IEEE BTAS, Arlington, VA, USA, September 2013.
    32. 32)
      • 27. Maatta, J., Hadid, A., Pietikäinen, M., et al: ‘Face spoofing detection from single images using texture and local shape analysis’, IET Biometrics, 2012, 1, (1), pp. 310.
    33. 33)
      • 25. Boulkenafet, Z., Komulainen, J., Li, L., et al: ‘A mobile face presentation attack database with real-world variations’. FG, Washington, DC, USA, May 2017.
    34. 34)
      • 30. ‘Lytro website’, Lytro Inc, 2017. Available at: https://www.lytro.com.
    35. 35)
      • 31. ‘Lytro Desktop 4’, Lytro, Inc. Available at: https://support.lytro.com/hc/en-us/articles/202590364-Lytro-Desktop-4-Main-Overview [Accessed April 2017].
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2017.0095
Loading

Related content

content/journals/10.1049/iet-bmt.2017.0095
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading