Occlusion-robust 3D face recognition using restoration and local classifiers

Nese Alyuz; B. Gökberk; Lieuwe Jan Spreeuwers; Raymond N.J. Veldhuis; Lale Akarun

doi:10.1109/SIU.2011.5929759

Occlusion-robust 3D face recognition using restoration and local classifiers

Nese Alyuz, B. Gökberk, Lieuwe Jan Spreeuwers, Raymond N.J. Veldhuis, Lale Akarun

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

3 Downloads (Pure)

Abstract

Occlusions complicate the process of identifying individuals using their 3D facial scans. We propose a 3D face recognition system that automatically removes occlusion artifacts and identifies the facial image using regional classifiers. Automatic localization of occluded areas is handled by using a generic face model. Restoration of missing information after occlusion removal is performed by the application of an improved version of Gappy Principal Component Analysis (GPCA), which we call partial Gappy PCA (pGPCA). After the removal of noisy data introduced by realistic occlusions, occlusion-free faces are represented by local regions. Local classifiers operating on these local regions are then fused to achieve occlusion-robust identification performance. Our experimental results obtained on realistically occluded facial images from the Bosphorus 3D face database illustrate that our occlusion compensation scheme drastically improves the recognition accuracy from 78.05% to 94.20%.

Original language	Undefined
Title of host publication	Proceedings of the 2011 IEEE 19th Conference on Signal Processing and Communications Applications (SIU 2011)
Place of Publication	USA
Publisher	IEEE
Pages	750-753
Number of pages	4
ISBN (Print)	978-1-4577-0462-8
DOIs	https://doi.org/10.1109/SIU.2011.5929759
Publication status	Published - 20 Apr 2011
Event	19th IEEE Conference on Signal Processing and Communications Applications, SIU 2011 - Antalya, Turkey Duration: 20 Apr 2011 → 22 Apr 2011

Publication series

Name
Publisher	IEEE Signal Processing Society

Conference

Conference	19th IEEE Conference on Signal Processing and Communications Applications, SIU 2011
Period	20/04/11 → 22/04/11
Other	20-22 April 2011

Keywords

IR-78805
METIS-281627
occlusion-robust 3D face recognition
occlusion artifact
Gappy principal component analysis
GPCA
restoration classifier
image identification
automatic localization
missing information Restoration
local classifier
partial Gappy PCA
pGPCA
generic face model
SCS-Safety
EWI-20961

Access to Document

10.1109/SIU.2011.5929759

http://eprints.eemcs.utwente.nl/secure2/20961/01/Alyuz11_Occlusion-robust_3D_face_recognition_using_restoration_and_local_classifiers.pdf

Cite this

@inproceedings{46973ed7dc67459ab509b199234b57a5,

title = "Occlusion-robust 3D face recognition using restoration and local classifiers",

abstract = "Occlusions complicate the process of identifying individuals using their 3D facial scans. We propose a 3D face recognition system that automatically removes occlusion artifacts and identifies the facial image using regional classifiers. Automatic localization of occluded areas is handled by using a generic face model. Restoration of missing information after occlusion removal is performed by the application of an improved version of Gappy Principal Component Analysis (GPCA), which we call partial Gappy PCA (pGPCA). After the removal of noisy data introduced by realistic occlusions, occlusion-free faces are represented by local regions. Local classifiers operating on these local regions are then fused to achieve occlusion-robust identification performance. Our experimental results obtained on realistically occluded facial images from the Bosphorus 3D face database illustrate that our occlusion compensation scheme drastically improves the recognition accuracy from 78.05% to 94.20%.",

keywords = "IR-78805, METIS-281627, occlusion-robust 3D face recognition, occlusion artifact, Gappy principal component analysis, GPCA, restoration classifier, image identification, automatic localization, missing information Restoration, local classifier, partial Gappy PCA, pGPCA, generic face model, SCS-Safety, EWI-20961",

author = "Nese Alyuz and B. G{\"o}kberk and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.} and Lale Akarun",

note = "In Turkish.; 19th IEEE Conference on Signal Processing and Communications Applications, SIU 2011 ; Conference date: 20-04-2011 Through 22-04-2011",

year = "2011",

month = apr,

day = "20",

doi = "10.1109/SIU.2011.5929759",

language = "Undefined",

isbn = "978-1-4577-0462-8",

publisher = "IEEE",

pages = "750--753",

booktitle = "Proceedings of the 2011 IEEE 19th Conference on Signal Processing and Communications Applications (SIU 2011)",

address = "United States",

}

Alyuz, N, Gökberk, B, Spreeuwers, LJ , Veldhuis, RNJ & Akarun, L 2011, Occlusion-robust 3D face recognition using restoration and local classifiers. in Proceedings of the 2011 IEEE 19th Conference on Signal Processing and Communications Applications (SIU 2011). IEEE, USA, pp. 750-753, 19th IEEE Conference on Signal Processing and Communications Applications, SIU 2011, 20/04/11. https://doi.org/10.1109/SIU.2011.5929759

Occlusion-robust 3D face recognition using restoration and local classifiers. / Alyuz, Nese; Gökberk, B.; Spreeuwers, Lieuwe Jan et al.
Proceedings of the 2011 IEEE 19th Conference on Signal Processing and Communications Applications (SIU 2011). USA: IEEE, 2011. p. 750-753.

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

TY - GEN

T1 - Occlusion-robust 3D face recognition using restoration and local classifiers

AU - Alyuz, Nese

AU - Gökberk, B.

AU - Spreeuwers, Lieuwe Jan

AU - Veldhuis, Raymond N.J.

AU - Akarun, Lale

N1 - In Turkish.

PY - 2011/4/20

Y1 - 2011/4/20

N2 - Occlusions complicate the process of identifying individuals using their 3D facial scans. We propose a 3D face recognition system that automatically removes occlusion artifacts and identifies the facial image using regional classifiers. Automatic localization of occluded areas is handled by using a generic face model. Restoration of missing information after occlusion removal is performed by the application of an improved version of Gappy Principal Component Analysis (GPCA), which we call partial Gappy PCA (pGPCA). After the removal of noisy data introduced by realistic occlusions, occlusion-free faces are represented by local regions. Local classifiers operating on these local regions are then fused to achieve occlusion-robust identification performance. Our experimental results obtained on realistically occluded facial images from the Bosphorus 3D face database illustrate that our occlusion compensation scheme drastically improves the recognition accuracy from 78.05% to 94.20%.

AB - Occlusions complicate the process of identifying individuals using their 3D facial scans. We propose a 3D face recognition system that automatically removes occlusion artifacts and identifies the facial image using regional classifiers. Automatic localization of occluded areas is handled by using a generic face model. Restoration of missing information after occlusion removal is performed by the application of an improved version of Gappy Principal Component Analysis (GPCA), which we call partial Gappy PCA (pGPCA). After the removal of noisy data introduced by realistic occlusions, occlusion-free faces are represented by local regions. Local classifiers operating on these local regions are then fused to achieve occlusion-robust identification performance. Our experimental results obtained on realistically occluded facial images from the Bosphorus 3D face database illustrate that our occlusion compensation scheme drastically improves the recognition accuracy from 78.05% to 94.20%.

KW - IR-78805

KW - METIS-281627

KW - occlusion-robust 3D face recognition

KW - occlusion artifact

KW - Gappy principal component analysis

KW - GPCA

KW - restoration classifier

KW - image identification

KW - automatic localization

KW - missing information Restoration

KW - local classifier

KW - partial Gappy PCA

KW - pGPCA

KW - generic face model

KW - SCS-Safety

KW - EWI-20961

U2 - 10.1109/SIU.2011.5929759

DO - 10.1109/SIU.2011.5929759

M3 - Conference contribution

SN - 978-1-4577-0462-8

SP - 750

EP - 753

BT - Proceedings of the 2011 IEEE 19th Conference on Signal Processing and Communications Applications (SIU 2011)

PB - IEEE

CY - USA

T2 - 19th IEEE Conference on Signal Processing and Communications Applications, SIU 2011

Y2 - 20 April 2011 through 22 April 2011

ER -