Skip to main content
SpringerLink
Log in

Defeating face de-identification methods based on DCT-block scrambling

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Face de-identification aims at preserving the privacy of people by concealing faces in images and videos. In this paper, we propose a defeating algorithm for face de-identification methods that are based on DCT-block scrambling. These methods protect faces by scrambling the AC and DC coefficients of the DCT blocks corresponding to a face region in the compressed domain. The proposed approach does not make use of the protection key utilized in the de-identification process. It consists of the following stages. First, random unprotected faces are generated based on a random alteration of the sign of AC coefficients with a fixed value of DC coefficients. Then, the best unprotected faces are selected by an eigenfaces model trained with facial images from a repository of potentially protected people. A single facial image is then generated by merging the selected images through median stacking. Finally, the eigenfaces model is utilized again to choose the face from the repository that is closest to the resulting image in order to improve the aspect of the unprotected face. Experimental results using a proprietary database and the public CALTECH, Utrecht and LFW face databases show the effectiveness of the proposed technique.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. In the compressed video stream, each group of pictures (GOP) starts with an I-frame (intra-coded) and contains several P-frames (predicted) and B-frames (bi-predictive). I-frames are stored and compressed entirely: the frame is divided into blocks of \(8\times 8\) pixels to which a frequency transform (e.g. Discrete Cosine Transform) is applied. The obtained \(8\times 8\) blocks describe the image block in terms of texture and contours. For each block, there is one (direct) DC and 63 (alternate) AC coefficients.

References

  1. Baaziz, N., Lolo, N., Padilla, O., Petngang, F.: Security and privacy protection for automated video surveillance. In: Signal processing and information technology, IEEE International symposium, pp. 17–22 (2007)

  2. Boyle, M., Edwards, C., Greenberg, S.: The effects of filtered video on awareness and privacy. In: Proceedings of the ACM conference on computer supported cooperative work, CSCW 2000 (2000)

  3. Dataset CFF (1991). http://www.vision.caltech.edu/html-files/archive.html

  4. Dufaux, F., Ebrahimi, T.: Scrambling for video surveillance with privacy. In: Computer vision and pattern recognition workshop, 2006. CVPRW ’06. Conference, pp. 160–160 (2006). doi:10.1109/CVPRW.2006.184

  5. Dufaux, F., Ebrahimi, T.: H.264/avc video scrambling for privacy protection. In: Image processing, 2008. ICIP 2008. 15th IEEE International Conference, pp. 1688–1691 (2008a). doi:10.1109/ICIP.2008.4712098

  6. Dufaux, F., Ebrahimi, T.: Scrambling for privacy protection in video surveillance systems. Circuits Syst Video Technol IEEE Trans. 18(8), 1168–1174 (2008b)

  7. Dufaux, F., Ouaret, M., Abdeljaoued, Y., Navarro, A., Vergnen, F., Ebrahimi, T.: Privacy enabling technology for video surveillance. In: Proc. SPIE 6250, mobile multimedia/image processing for military and security applications (2006)

  8. European conference on visual perception DFSUE (2007). http://pics.psych.stir.ac.uk/2d_face_sets.htm

  9. Fukuoka, N., Ito, Y., Babaguchi, N.: Delivery method for viewer-specific privacy protected video using discrete wavelet transform. In: Image processing (ICIP), 2012 19th IEEE International conference, pp. 2285–2288 (2012). doi:10.1109/ICIP.2012.6467352

  10. Gabbouj, M., Coyle, E.J., Gallagher, N.C.: An overview of median and stack filtering. In: Circuits, systems, and signal processing, special issue on median and morphological filtering, pp. 7–45 (1992)

  11. Gross, R., Sweeney, L., Cohn, J.F., De la Torre, F., Baker, S.: Protecting privacy in video surveillance.Springer Publishing Company, Incorporated, chap Face De-identification, pp. 129–146 (2009)

  12. Hadid, A., Pietikinen, M., Ahonen, T.: A discriminative feature space for detecting and recognizing faces. In: IEEE computer society conference on computer vision and pattern, IEEE Computer Society, pp. 797–804 (2004)

  13. Huang, G.B., Jain, V., Learned-Miller, E.: Unsupervised joint alignment of complex images. In: ICCV (2007)

  14. Korshunov, P., Ebrahimi, T.: Using face morphing to protect privacy. In: Advanced video and signal based surveillance (AVSS), 2013 10th IEEE International Conference, pp. 208–213 (2013)

  15. Martínez-Ballesté, A., Rashwan, H.A., Puig, D., Paniza Fullana, A.: Towards a trustworthy privacy in pervasive video surveillance systems. In: IEEE International conference on pervasive computing and communications workshops (PERCOM Workshops), 2012, pp. 914–919 (2012)

  16. Martínez-ballesté, A., Rashwan, H.A., Castellà-Roca, J., Puig, D.: A trustworthy database for privacy-preserving video surveillance. In: Privacy and anonymity in the information society–PAIS 2013—Proceedings of the Joint EDBT/ICDT 2013 Workshops, pp. 179–183 (2013)

  17. Martínez-Ballesté, A., Solanas, A., Rashwan, H.A.: Advanced research in data privacy, Springer International Publishing, Incorporated, chap trustworthy video surveillance: an approach based on guaranteeing data privacy, pp. 271–284 (2015)

  18. Newton, E., Sweeney, L., Malin, B.: Preserving privacy by de-identifying face images. Knowl. Data Eng. IEEE Trans. 17(2), 232–243 (2005). doi:10.1109/TKDE.2005.32

    Article  Google Scholar 

  19. Ponte, I.M., Desurmont, X., Meessen, J., Francois Delaigle J.: Robust human face hiding ensuring privacy. In: in Proc. of international workshop on image analysis for multimedia interactive services (WIAMIS) (2005)

  20. Rao, K.R., Yip, P.: Discrete cosine transform: algorithms, advantages, applications.Academic Press Professional Inc, San Diego (1990)

  21. Rashwan, H.A., Solanas, A., Puig, D., Martínez-Ballesté, A.: Understanding trust in privacy-aware video surveillance systems. Int. J. Inf. Secur., pp. 1–10 (2015)

  22. Sohn, H., Anzaku, E.T., De Neve, W., Ro, Y.M., Plataniotis, K.N.: Privacy protection in video surveillance systems using scalable video coding. In: 2009 Sixth IEEE international conference on advanced video and signal based surveillance, Ieee, pp. 424–429 (2009)

  23. Sohn, H., De Neve, W., Ro, Y.M.: Privacy protection in video surveillance systems: analysis of subband-adaptive scrambling in jpeg xr. Circuits Syst Video Technol IEEE Trans 21(2), 170–177 (2011). doi:10.1109/TCSVT.2011.2106250

    Article  Google Scholar 

  24. Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991). doi:10.1162/jocn.1991.3.1.71

    Article  Google Scholar 

  25. Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. Comput. Vis. Pattern Recogn. Proc. IEEE Comput. Soc. Conf. 1, 511–518 (2001). doi:10.1109/CVPR.2001.990517

    Google Scholar 

  26. Wickramasuriya, J., Datt, M., Mehrotra, S., Venkatasubramanian, N.: Privacy protecting data collection in media spaces. In: Proceedings of the 12th Annual ACM international conference on multimedia, MULTIMEDIA ’04, pp. 48–55. ACM, New York (2004)

  27. Zhao, Q.A., Stasko, J.T.: Evaluating image filtering based techniques in media space applications. In: Proceedings of the 1998 ACM conference on computer supported cooperative work, CSCW ’98, pp. 11–18. ACM, New York (1998)

Download references

Author information

Authors and Affiliations

  1. Vortex, CNRS-IRIT, ENSEEIHT-INP, Université de Toulouse, Toulouse, France

    Hatem A. Rashwan

  2. VPU, Universidad Autònoma de Madrid, Madrid, Spain

    Miguel Angel García

  3. DEIM, Universitat Rovira i Virgili, Tarragona, Spain

    Antoni Martínez-Ballesté & Domènec Puig

Authors
  1. Hatem A. Rashwan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Miguel Angel García
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Antoni Martínez-Ballesté
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Domènec Puig
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hatem A. Rashwan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rashwan, H.A., García, M.A., Martínez-Ballesté, A. et al. Defeating face de-identification methods based on DCT-block scrambling. Machine Vision and Applications 27, 251–262 (2016). https://doi.org/10.1007/s00138-015-0743-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-015-0743-5

Keywords

Search

Navigation