De-identifying facial images using projections on hyperspheres

A major issue that arises from mass visual media distribution in modern video sharing, social media and cloud services, is the issue of privacy. Malicious users can use these services to track the actions of certain individuals and/or groups thus violating their privacy. As a result the need to hind...

Full description

Saved in:
Bibliographic Details
Published in2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) Vol. 4; pp. 1 - 6
Main Authors Chriskos, P., Zoidi, O., Tefas, A., Pitas, I.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2015
Subjects
Error analysis
Face
Face recognition
Media
Privacy
Visualization
Online AccessGet full text
DOI10.1109/FG.2015.7285020

Cover

More Information
Summary:A major issue that arises from mass visual media distribution in modern video sharing, social media and cloud services, is the issue of privacy. Malicious users can use these services to track the actions of certain individuals and/or groups thus violating their privacy. As a result the need to hinder automatic facial image identification in images and videos arises. In this paper we propose a method for de-identifying facial images. Contrary to most de-identification methods, this method manipulates facial images so that humans can still recognize the individual or individuals in an image or video frame, but at the same time common automatic identification algorithms fail to do so. This is achieved by projecting the facial images on a hypersphere. From the conducted experiments it can be verified that this method is effective in reducing the classification accuracy under 10%. Furthermore, in the resulting images the subject can be identified by human viewers.
DOI:10.1109/FG.2015.7285020