Distinguishable de-identified faces

Zongji Sun; Li Meng; A. Ariyaeeinia

doi:10.1109/FG.2015.7285019

Distinguishable de-identified faces

Zongji Sun
, Li Meng
, A. Ariyaeeinia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

33 Citations (Scopus)

210 Downloads (Pure)

Abstract

The k-anonymity approach adopted by k-Same face de-identification methods enables these methods to serve their purpose of privacy protection. However, it also forces every k original faces to share the same de-identified face, making it impossible to track individuals in a k-Same de-identified video. To address this issue, this paper presents an approach to the creation of distinguishable de-identified faces. This new approach can serve privacy protection perfectly whilst producing de-identified faces that are as distinguishable as their original faces.

Original language	English
Title of host publication	Procs 2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG)
Place of Publication	IEEE
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	6
Volume	4
ISBN (Print)	978-1-4799-6026-2
DOIs	https://doi.org/10.1109/FG.2015.7285019
Publication status	Published - May 2015
Event	2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG) - Ljubljana, Slovenia Duration: 4 May 2015 → 8 May 2015

Conference

Conference	2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG)
Country/Territory	Slovenia
City	Ljubljana
Period	4/05/15 → 8/05/15

Keywords

Biometrics
PRIVACY PROTECTION
Data Security

Access to Document

10.1109/FG.2015.7285019

Full Text: Distinguishable de-identified facesFinal published version, 1.62 MB

Cite this

@inproceedings{a22f0178c89d43cd99afa3d60468b340,

title = "Distinguishable de-identified faces",

abstract = "The k-anonymity approach adopted by k-Same face de-identification methods enables these methods to serve their purpose of privacy protection. However, it also forces every k original faces to share the same de-identified face, making it impossible to track individuals in a k-Same de-identified video. To address this issue, this paper presents an approach to the creation of distinguishable de-identified faces. This new approach can serve privacy protection perfectly whilst producing de-identified faces that are as distinguishable as their original faces.",

keywords = "Biometrics, PRIVACY PROTECTION, Data Security",

author = "Zongji Sun and Li Meng and A. Ariyaeeinia",

year = "2015",

month = may,

doi = "10.1109/FG.2015.7285019",

language = "English",

isbn = "978-1-4799-6026-2",

volume = "4",

booktitle = "Procs 2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG) ; Conference date: 04-05-2015 Through 08-05-2015",

}

Sun, Z, Meng, L & Ariyaeeinia, A 2015, Distinguishable de-identified faces. in Procs 2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG). vol. 4, Institute of Electrical and Electronics Engineers (IEEE), IEEE, 2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG), Ljubljana, Slovenia, 4/05/15. https://doi.org/10.1109/FG.2015.7285019

TY - GEN

T1 - Distinguishable de-identified faces

AU - Sun, Zongji

AU - Meng, Li

AU - Ariyaeeinia, A.

PY - 2015/5

Y1 - 2015/5

N2 - The k-anonymity approach adopted by k-Same face de-identification methods enables these methods to serve their purpose of privacy protection. However, it also forces every k original faces to share the same de-identified face, making it impossible to track individuals in a k-Same de-identified video. To address this issue, this paper presents an approach to the creation of distinguishable de-identified faces. This new approach can serve privacy protection perfectly whilst producing de-identified faces that are as distinguishable as their original faces.

AB - The k-anonymity approach adopted by k-Same face de-identification methods enables these methods to serve their purpose of privacy protection. However, it also forces every k original faces to share the same de-identified face, making it impossible to track individuals in a k-Same de-identified video. To address this issue, this paper presents an approach to the creation of distinguishable de-identified faces. This new approach can serve privacy protection perfectly whilst producing de-identified faces that are as distinguishable as their original faces.

KW - Biometrics

KW - PRIVACY PROTECTION

KW - Data Security

U2 - 10.1109/FG.2015.7285019

DO - 10.1109/FG.2015.7285019

M3 - Conference contribution

SN - 978-1-4799-6026-2

VL - 4

BT - Procs 2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - IEEE

T2 - 2015 11th IEEE Int Conf and Workshops on Automatic Face and Gesture Recognition (FG)

Y2 - 4 May 2015 through 8 May 2015

ER -

Distinguishable de-identified faces

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this