Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition

A. Nasser Ansari; Mohammad H. Mahoor; Mohamed Abdel-Mottaleb

doi:10.1109/IEEEGCC.2011.5752482

Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition

A. Nasser Ansari, Mohammad H. Mahoor, Mohamed Abdel-Mottaleb

Electrical and Computer Engineering

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

4 Scopus citations

Abstract

In our previous research [13], we created a database of 3D textured face models of people using stereo images and a generic face mesh model for 3D face recognition application. Consequently, in this paper we make use of this available database and propose an algorithm for synthesizing multiple view 2D facial images of each subject, which extends the number of images used in the training stage of a 2D face recognition system. The main contributions of our work are: a) proposing a novel 3D model-based face pose and scale normalizations before creating the synthesized 2D database from its 3D counterpart and b) proposing a model-based facial area segmentation and normalization to a given 2D probe facial image. Recognition experiments, using near frontal probe facial images and the extended synthesized database, demonstrate improved 2D recognition rate.

Original language	English (US)
Title of host publication	2011 IEEE GCC Conference and Exhibition, GCC
Pages	178-181
Number of pages	4
DOIs	https://doi.org/10.1109/IEEEGCC.2011.5752482
State	Published - Jun 9 2011
Event	2011 IEEE GCC Conference and Exhibition, GCC 2011 - Dubai, United Arab Emirates Duration: Feb 19 2011 → Feb 22 2011

Publication series

Name	2011 IEEE GCC Conference and Exhibition, GCC 2011

Other

Other	2011 IEEE GCC Conference and Exhibition, GCC 2011
Country	United Arab Emirates
City	Dubai
Period	2/19/11 → 2/22/11

Keywords

Face analysis
face normalization
face pose
face recognition
face synthesis

ASJC Scopus subject areas

Hardware and Architecture
Signal Processing
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/IEEEGCC.2011.5752482

Fingerprint Dive into the research topics of 'Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition'. Together they form a unique fingerprint.

Cite this

Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition. / Ansari, A. Nasser; Mahoor, Mohammad H.; Abdel-Mottaleb, Mohamed.

2011 IEEE GCC Conference and Exhibition, GCC. 2011. p. 178-181 5752482 (2011 IEEE GCC Conference and Exhibition, GCC 2011).

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

Ansari, AN, Mahoor, MH & Abdel-Mottaleb, M 2011, Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition. in 2011 IEEE GCC Conference and Exhibition, GCC., 5752482, 2011 IEEE GCC Conference and Exhibition, GCC 2011, pp. 178-181, 2011 IEEE GCC Conference and Exhibition, GCC 2011, Dubai, United Arab Emirates, 2/19/11. https://doi.org/10.1109/IEEEGCC.2011.5752482

@inproceedings{c1d99b5e9543474e8c85892aa5bac058,

title = "Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition",

abstract = "In our previous research [13], we created a database of 3D textured face models of people using stereo images and a generic face mesh model for 3D face recognition application. Consequently, in this paper we make use of this available database and propose an algorithm for synthesizing multiple view 2D facial images of each subject, which extends the number of images used in the training stage of a 2D face recognition system. The main contributions of our work are: a) proposing a novel 3D model-based face pose and scale normalizations before creating the synthesized 2D database from its 3D counterpart and b) proposing a model-based facial area segmentation and normalization to a given 2D probe facial image. Recognition experiments, using near frontal probe facial images and the extended synthesized database, demonstrate improved 2D recognition rate.",

keywords = "Face analysis, face normalization, face pose, face recognition, face synthesis",

author = "Ansari, {A. Nasser} and Mahoor, {Mohammad H.} and Mohamed Abdel-Mottaleb",

year = "2011",

month = jun,

day = "9",

doi = "10.1109/IEEEGCC.2011.5752482",

language = "English (US)",

isbn = "9781612841199",

series = "2011 IEEE GCC Conference and Exhibition, GCC 2011",

pages = "178--181",

booktitle = "2011 IEEE GCC Conference and Exhibition, GCC",

note = "2011 IEEE GCC Conference and Exhibition, GCC 2011 ; Conference date: 19-02-2011 Through 22-02-2011",

}

TY - GEN

T1 - Normalized 3D to 2D model-based facial image synthesis for 2D model-based face recognition

AU - Ansari, A. Nasser

AU - Mahoor, Mohammad H.

AU - Abdel-Mottaleb, Mohamed

PY - 2011/6/9

Y1 - 2011/6/9

N2 - In our previous research [13], we created a database of 3D textured face models of people using stereo images and a generic face mesh model for 3D face recognition application. Consequently, in this paper we make use of this available database and propose an algorithm for synthesizing multiple view 2D facial images of each subject, which extends the number of images used in the training stage of a 2D face recognition system. The main contributions of our work are: a) proposing a novel 3D model-based face pose and scale normalizations before creating the synthesized 2D database from its 3D counterpart and b) proposing a model-based facial area segmentation and normalization to a given 2D probe facial image. Recognition experiments, using near frontal probe facial images and the extended synthesized database, demonstrate improved 2D recognition rate.

AB - In our previous research [13], we created a database of 3D textured face models of people using stereo images and a generic face mesh model for 3D face recognition application. Consequently, in this paper we make use of this available database and propose an algorithm for synthesizing multiple view 2D facial images of each subject, which extends the number of images used in the training stage of a 2D face recognition system. The main contributions of our work are: a) proposing a novel 3D model-based face pose and scale normalizations before creating the synthesized 2D database from its 3D counterpart and b) proposing a model-based facial area segmentation and normalization to a given 2D probe facial image. Recognition experiments, using near frontal probe facial images and the extended synthesized database, demonstrate improved 2D recognition rate.

KW - Face analysis

KW - face normalization

KW - face pose

KW - face recognition

KW - face synthesis

UR - http://www.scopus.com/inward/record.url?scp=79957979232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957979232&partnerID=8YFLogxK

U2 - 10.1109/IEEEGCC.2011.5752482

DO - 10.1109/IEEEGCC.2011.5752482

M3 - Conference contribution

AN - SCOPUS:79957979232

SN - 9781612841199

T3 - 2011 IEEE GCC Conference and Exhibition, GCC 2011

SP - 178

EP - 181

BT - 2011 IEEE GCC Conference and Exhibition, GCC

T2 - 2011 IEEE GCC Conference and Exhibition, GCC 2011

Y2 - 19 February 2011 through 22 February 2011

ER -