Graduate School and Research Center in Digital Sciences

Scrambling faces for privacy protection using background self-similarities

Melle, Andrea; Dugelay, Jean-Luc

ICIP 2014, IEEE International Conference on Image Processing, October 27-30, 2014, Paris, France

The pervasive adoption of video surveillance systems demands tools for protecting the privacy of the persons being monitored. Current solutions are either naïve or they lack of important characteristics, such as reversibility or visual quality preservation. In this paper, we propose a novel scrambling procedure for protecting privacy sensitive image regions, which encodes the sensitive data in a parametric form, exploiting the visual information in the remaining part of the image. The encoded data is encrypted with a secret key. Partial knowledge of encryption key gives a protected version of the original image at variable levels of scrambling, while the knowledge of the full key allows decryption to a quality level suitable for people identification. To evaluate the proposed approach, we apply our scrambling filter to the AT&T face recognition dataset and we measure the resulting quality with an objective metric.

Doi Bibtex

Title:Scrambling faces for privacy protection using background self-similarities
Keywords:Privacy protection, video surveillance, face scrambling
Department:Digital Security
Eurecom ref:4426
Copyright: © 2014 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+4426, doi = {}, year = {2014}, title = {{S}crambling faces for privacy protection using background self-similarities}, author = {{M}elle, {A}ndrea and {D}ugelay, {J}ean-{L}uc}, booktitle = {{ICIP} 2014, {IEEE} {I}nternational {C}onference on {I}mage {P}rocessing, {O}ctober 27-30, 2014, {P}aris, {F}rance}, address = {{P}aris, {FRANCE}}, month = {10}, url = {} }
See also: