Utility Preserved Facial Image De-identification Using Appearance Subspace Decomposition

LIU Chuanlu; WANG Yicheng; CHI Hehua; WANG Shuliang

doi:10.1049/cje.2021.03.004

Volume 30 Issue 3

May 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2021 > 30(3): 413-418

LIU Chuanlu, WANG Yicheng, CHI Hehua, et al., “Utility Preserved Facial Image De-identification Using Appearance Subspace Decomposition,” Chinese Journal of Electronics, vol. 30, no. 3, pp. 413-418, 2021, doi: 10.1049/cje.2021.03.004

Citation:

LIU Chuanlu, WANG Yicheng, CHI Hehua, et al., “Utility Preserved Facial Image De-identification Using Appearance Subspace Decomposition,” Chinese Journal of Electronics, vol. 30, no. 3, pp. 413-418, 2021, doi: 10.1049/cje.2021.03.004

Citation:

PDF( 484 KB)

Utility Preserved Facial Image De-identification Using Appearance Subspace Decomposition

doi: 10.1049/cje.2021.03.004

1. School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China;
2. Institute of E-Government, Beijing Institute of Technology, Beijing 100081, China;
3. Wuhan University, Wuhan 430000, China

Funds:

This work was supported by Science and Technology Innovation Research Project of The Ministry of Science and Technology of China (No.ZLY201970, No.ZLY201976-02).

Received Date: 2019-05-05

Abstract

Abstract

Automated human facial image deidentification is a much-needed technology for privacy-preserving social media and intelligent surveillance applications. We propose a novel utility preserved facial image de-identification to subtly tinker the appearance of facial images to achieve facial anonymity by creating “averaged identity faces”. This approach is able to preserve the utility of the facial images while achieving the goal of privacy protection. We explore a decomposition of an Active appearance model (AAM) face space by using subspace learning where the loss can be modeled as the difference between two trace ratio items, and each respectively models the level of discriminativeness on identity and utility. Finally, the face space is decomposed into subspaces that are respectively sensitive to face identity and face utility. For the subspace most relevant to face identity, a k-anonymity de-identification procedure is applied. To verify the performance of the proposed facial image de-identification approach, we evaluate the created “ averaged faces” using the extended Cohn-Kanade Dataset (CK+). The experimental results show that our proposed approach is satisfied to preserve the utility of the original image while defying face identity recognition.
- Face recognition,
- face expression,
- face utility,
- data privacy,
- active appearance model

FullText(HTML)

References(18)

References

J. Moran,“Citizenship and identity in the age of surveillance”, Journal of Postcolonial Writing, Vol.51, No.6, pp.749–750, 2015.

R. Agrawal and S. Ramakrishnan,“Privacy-preserving data mining”, Proceedings of the 2000 ACM SIGMOD International Conference on Management of data, 2000.

C. Neustaedter, S. Greenberg and M. Boyle, “Blur filtration fails to preserve privacy for home-based video conferencing”, ACM Transactions on Computer-Human Interaction, Vol.13, No.1, pp.1–36, 2006.

D. Netburn,“Youtube’ s new face-blurring tool designed to protect activists”, Activists, Los Angeles Times, LA, USA, July, 2012.

R. Slobodan and N. Pavesic,“An overview of face deidentification in still images and videos”, Automatic Face and Gesture Recognition (FG), Vol.4, pp.1–6, 2015.

E. Newton, L. Sweeney and B. Malin,“Preserving privacy by De-identifying facial images”, IEEE Transactions Knowledge and Data Engineering, Vol.19, No.2, pp.232–243, 2005.

R. Gross, E. Airoldi, B. Malin, et al., “Integrating utility into face de-identification”, Proceedings of International Workshop on Privacy Enhancing Technologies, Vol.16, No.8, pp.227–242, 2005.

R. Gross, L. Sweeney, F. de la Torre, et al., “Model-based face de-identification”, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.161–161, 2006.

R. Gross and L. Sweeney, “Model-based face deidentification”, Proceedings of IEEE Conference on Biometrics: Theory, Applications, and Systems, pp.1–8, 2007.

L. Sweeney, “k-anonymity: A model for protecting privacy”, International Journal on Uncertainty, Fuzziness and Knowledge-based Systems, Vol.10, No.5, pp.557–570, 2002.

H.H Chi and H.H Yu, “Face de-identification using facial identity preserving features”, Proceedings of 2015 IEEE Global Conference on Signal and Information Processing, pp.586–590, 2015.

A.J Calder, A.M Burton, P. Miller, et al., “Integrating utility into face De-identification”, Vision research, Vol.41, No.9, pp.1179–1208, 2001.

T. Cootes, G. Edwards and C. Taylor, “Active appearance models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.23, No.6, pp.681–685, 2001.

I. Matthews and S. Baker, “Active appearance models revisited”, International Journal of Comput Vision, Vol.60, No.2, pp.135–164, 2004.

I. Guyon and A. Elisseeff, “An introduction to variable and feature selection”, Journal of Machine Learning Research, Vol.3,No.3, pp.1157–1182, 2003.

P. Lucey, J.F Cohn, T. Kanade, et al., “The extended cohn-kanade dataset (CK+): A complete dataset for action unit and emotion-specified expression”, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.94–101, 2010.

G. Formam, “An extensive empirical study of feature selection metrics for text classification”, Journal of Machine Learning Research 3, pp.1289–1305, 2003.

Y. Yang and J.O Pedersen, “A comparative study on feature selection in text categorization”, Proceedings of the 14th International Conference on Machine Learning, pp.412–420, 1997.

Relative Articles

Supplements(0)

Cited By

Proportional views