De-Identifying Facial Images Using Projections on Hyperspheres

P. Chriskos, O. Zoidi, A. Tefas, Ioannis Pitas

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

2 Citations (Scopus)
363 Downloads (Pure)


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.
Original languageEnglish
Title of host publication2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG 2015)
Subtitle of host publicationProceedings of a meeting held 4-8 May 2015, Ljubljana, Slovenia
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)9781479960262
ISBN (Print)9781479960279
Publication statusPublished - Aug 2015
EventAutomatic Face and Gesture Recognition (FG), 11th IEEE International Conference and Workshops - Ljubljana, Slovenia
Duration: 4 May 20158 May 2015


ConferenceAutomatic Face and Gesture Recognition (FG), 11th IEEE International Conference and Workshops


Dive into the research topics of 'De-Identifying Facial Images Using Projections on Hyperspheres'. Together they form a unique fingerprint.

Cite this