Towards Face De-identification for Wearable Cameras

Conference proceedings article

Authors/Editors

Strategic Research Themes

Publication Details

Author list: Puangthamawathanakun, Bunyarit; Arpnikanondt, Chonlameth; Krathu, Worarat; Healy, Graham; Gurrin, Cathal;

Publisher: Association for Computing Machinery

Publication year: 2023

Start page: 210

End page: 216

Number of pages: 7

ISBN: 979-840070912-8

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85182596654&doi=10.1145%2f3617233.3617276&partnerID=40&md5=9841cdddd5e60e628f89fc085f04b722

Languages: English-Great Britain (EN-GB)

View on publisher site

Abstract

Wearable cameras provide valuable new sources of data for health and wellness monitoring, however, such visual data brings privacy concerns. This paper proposes a prototype egocentric face de-identification system for wearable camera images by swapping the original faces with synthetic faces. The motivation of this paper is to: (1) de-identify faces in egocentric images and (2) preserve the existence of each identity in images where the source identity is altered. The system incorporates our proposed method, which promises a privacy-aware and cost-effective approach. We evaluated the system on the Ego4D audio-visual PoV diarization training set by analysing six activities where faces are visible in wearable camera data. The results show promising de-identification on the source faces while most existences remain. ฉ 2023 Owner/Author.

Keywords

Face De-identification, Lifelog, Privacy