Privacy Protection Performance of De-identified Face Images with and without Background

Zongji Sun; Li Meng; Aladdin Ariyaeeinia; Xiaodong Duan; Zheng-Hua Tan

doi:10.1109/MIPRO.2016.7522350

Privacy Protection Performance of De-identified Face Images with and without Background

Zongji Sun, Li Meng, Aladdin Ariyaeeinia, Xiaodong Duan, Zheng-Hua Tan

Centre for Engineering Research

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

2 Citations (Scopus)

189 Downloads (Pure)

Abstract

This paper presents an approach to blending a de-identified face region with its original background, for the purpose of completing the process of face de-identification. The re-identification risk of the de-identified FERET face images has been evaluated for the k-Diff-furthest face de-identification method, using several face recognition benchmark methods including PCA, LBP, HOG and LPQ. The experimental results show that the k-Diff-furthest face de-identification delivers high privacy protection within the face region while blending the de-identified face region with its original background may significantly increases the re-identification risk, indicating that de-identification must also be applied to image areas beyond the face region.

Original language	English
Title of host publication	39th Intl. ICT (Information and Communication Technology) Convention MIPRO 2016
Place of Publication	Croatia
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1354
Number of pages	1359
ISBN (Print)	978-953-233-088-5
DOIs	https://doi.org/10.1109/MIPRO.2016.7522350
Publication status	Published - 31 May 2016
Event	The 39th International ICT Convention - MIPRO 2016 - Grand hotel Adriatic Congress Centre and Hotel Admiral, Opatija, Croatia Duration: 30 May 2016 → 1 Jun 2016 http://mipro-proceedings.com/

Conference

Conference	The 39th International ICT Convention - MIPRO 2016
Country/Territory	Croatia
City	Opatija
Period	30/05/16 → 1/06/16
Internet address	http://mipro-proceedings.com/

Access to Document

10.1109/MIPRO.2016.7522350

meng-et-al2Accepted author manuscript, 702 KBLicence: Other

Cite this

@inproceedings{a5a33f58256b407984acdc08d6242ca8,

title = "Privacy Protection Performance of De-identified Face Images with and without Background",

abstract = "This paper presents an approach to blending a de-identified face region with its original background, for the purpose of completing the process of face de-identification. The re-identification risk of the de-identified FERET face images has been evaluated for the k-Diff-furthest face de-identification method, using several face recognition benchmark methods including PCA, LBP, HOG and LPQ. The experimental results show that the k-Diff-furthest face de-identification delivers high privacy protection within the face region while blending the de-identified face region with its original background may significantly increases the re-identification risk, indicating that de-identification must also be applied to image areas beyond the face region.",

author = "Zongji Sun and Li Meng and Aladdin Ariyaeeinia and Xiaodong Duan and Zheng-Hua Tan",

note = "Li Meng, 'Privacy Protection Performance of De-identified Face Images with and without Background', paper presented at the 39th International Information and Communication Technology (ICT) Convention. Grand Hotel Adriatic Congress Centre and Admiral Hotel, Opatija, Croatia, May 30 - June 3, 2016.; The 39th International ICT Convention - MIPRO 2016 ; Conference date: 30-05-2016 Through 01-06-2016",

year = "2016",

month = may,

day = "31",

doi = "10.1109/MIPRO.2016.7522350",

language = "English",

isbn = "978-953-233-088-5",

pages = "1354",

booktitle = "39th Intl. ICT (Information and Communication Technology) Convention MIPRO 2016",

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

address = "United States",

url = "http://mipro-proceedings.com/",

}

Sun, Z, Meng, L , Ariyaeeinia, A, Duan, X & Tan, Z-H 2016, Privacy Protection Performance of De-identified Face Images with and without Background. in 39th Intl. ICT (Information and Communication Technology) Convention MIPRO 2016. Institute of Electrical and Electronics Engineers (IEEE), Croatia , pp. 1354, The 39th International ICT Convention - MIPRO 2016, Opatija, Croatia, 30/05/16. https://doi.org/10.1109/MIPRO.2016.7522350

Privacy Protection Performance of De-identified Face Images with and without Background. / Sun, Zongji; Meng, Li ; Ariyaeeinia, Aladdin et al.
39th Intl. ICT (Information and Communication Technology) Convention MIPRO 2016. Croatia : Institute of Electrical and Electronics Engineers (IEEE), 2016. p. 1354.

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

TY - GEN

T1 - Privacy Protection Performance of De-identified Face Images with and without Background

AU - Sun, Zongji

AU - Meng, Li

AU - Ariyaeeinia, Aladdin

AU - Duan, Xiaodong

AU - Tan, Zheng-Hua

N1 - Li Meng, 'Privacy Protection Performance of De-identified Face Images with and without Background', paper presented at the 39th International Information and Communication Technology (ICT) Convention. Grand Hotel Adriatic Congress Centre and Admiral Hotel, Opatija, Croatia, May 30 - June 3, 2016.

PY - 2016/5/31

Y1 - 2016/5/31

N2 - This paper presents an approach to blending a de-identified face region with its original background, for the purpose of completing the process of face de-identification. The re-identification risk of the de-identified FERET face images has been evaluated for the k-Diff-furthest face de-identification method, using several face recognition benchmark methods including PCA, LBP, HOG and LPQ. The experimental results show that the k-Diff-furthest face de-identification delivers high privacy protection within the face region while blending the de-identified face region with its original background may significantly increases the re-identification risk, indicating that de-identification must also be applied to image areas beyond the face region.

AB - This paper presents an approach to blending a de-identified face region with its original background, for the purpose of completing the process of face de-identification. The re-identification risk of the de-identified FERET face images has been evaluated for the k-Diff-furthest face de-identification method, using several face recognition benchmark methods including PCA, LBP, HOG and LPQ. The experimental results show that the k-Diff-furthest face de-identification delivers high privacy protection within the face region while blending the de-identified face region with its original background may significantly increases the re-identification risk, indicating that de-identification must also be applied to image areas beyond the face region.

U2 - 10.1109/MIPRO.2016.7522350

DO - 10.1109/MIPRO.2016.7522350

M3 - Conference contribution

SN - 978-953-233-088-5

SP - 1354

BT - 39th Intl. ICT (Information and Communication Technology) Convention MIPRO 2016

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Croatia

T2 - The 39th International ICT Convention - MIPRO 2016

Y2 - 30 May 2016 through 1 June 2016

ER -

Privacy Protection Performance of De-identified Face Images with and without Background

Abstract

Conference

Access to Document

Fingerprint

Cite this