Disparity-based 3D face modeling for 3D face recognition

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We present an automatic disparity-based approach for 3D face modeling, from two frontal and one profile view stereo images, for 3D face recognition applications. Once the images are captured, the algorithm starts by extracting selected 2D facial features from one of the frontal views and computes a dense disparity map from the two frontal images. We then align a low resolution 2D mesh model to the selected features, adjust some of its vertices along the profile line using the profile view, increase its triangular vertices to a higher resolution, and re-project them back on the frontal image. Using the coordinates of the re-projected vertices and their corresponding disparities, we capture and compute the 3D facial shape variations using stereo vision. The final result is a deformed 3D model specific to a given subject's face. Application of the model in 3D face recognition validates the algorithm and shows a promising 98 % recognition rate.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages657-660
Number of pages4
DOIs
StatePublished - Dec 1 2006
Event2006 IEEE International Conference on Image Processing, ICIP 2006 - Atlanta, GA, United States
Duration: Oct 8 2006Oct 11 2006

Other

Other2006 IEEE International Conference on Image Processing, ICIP 2006
CountryUnited States
CityAtlanta, GA
Period10/8/0610/11/06

Fingerprint

Face recognition
Stereo vision

Keywords

  • 3D face modeling
  • Face recognition

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Ansari, A. N., Abdel-Mottaleb, M., & Mahoor, M. H. (2006). Disparity-based 3D face modeling for 3D face recognition. In Proceedings - International Conference on Image Processing, ICIP (pp. 657-660). [4106615] https://doi.org/10.1109/ICIP.2006.312416

Disparity-based 3D face modeling for 3D face recognition. / Ansari, A. Nasser; Abdel-Mottaleb, Mohamed; Mahoor, Mohammad H.

Proceedings - International Conference on Image Processing, ICIP. 2006. p. 657-660 4106615.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ansari, AN, Abdel-Mottaleb, M & Mahoor, MH 2006, Disparity-based 3D face modeling for 3D face recognition. in Proceedings - International Conference on Image Processing, ICIP., 4106615, pp. 657-660, 2006 IEEE International Conference on Image Processing, ICIP 2006, Atlanta, GA, United States, 10/8/06. https://doi.org/10.1109/ICIP.2006.312416
Ansari AN, Abdel-Mottaleb M, Mahoor MH. Disparity-based 3D face modeling for 3D face recognition. In Proceedings - International Conference on Image Processing, ICIP. 2006. p. 657-660. 4106615 https://doi.org/10.1109/ICIP.2006.312416
Ansari, A. Nasser ; Abdel-Mottaleb, Mohamed ; Mahoor, Mohammad H. / Disparity-based 3D face modeling for 3D face recognition. Proceedings - International Conference on Image Processing, ICIP. 2006. pp. 657-660
@inproceedings{8fd8f6fc70094754adccddd82c00ee39,
title = "Disparity-based 3D face modeling for 3D face recognition",
abstract = "We present an automatic disparity-based approach for 3D face modeling, from two frontal and one profile view stereo images, for 3D face recognition applications. Once the images are captured, the algorithm starts by extracting selected 2D facial features from one of the frontal views and computes a dense disparity map from the two frontal images. We then align a low resolution 2D mesh model to the selected features, adjust some of its vertices along the profile line using the profile view, increase its triangular vertices to a higher resolution, and re-project them back on the frontal image. Using the coordinates of the re-projected vertices and their corresponding disparities, we capture and compute the 3D facial shape variations using stereo vision. The final result is a deformed 3D model specific to a given subject's face. Application of the model in 3D face recognition validates the algorithm and shows a promising 98 {\%} recognition rate.",
keywords = "3D face modeling, Face recognition",
author = "Ansari, {A. Nasser} and Mohamed Abdel-Mottaleb and Mahoor, {Mohammad H.}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICIP.2006.312416",
language = "English",
isbn = "1424404819",
pages = "657--660",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Disparity-based 3D face modeling for 3D face recognition

AU - Ansari, A. Nasser

AU - Abdel-Mottaleb, Mohamed

AU - Mahoor, Mohammad H.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - We present an automatic disparity-based approach for 3D face modeling, from two frontal and one profile view stereo images, for 3D face recognition applications. Once the images are captured, the algorithm starts by extracting selected 2D facial features from one of the frontal views and computes a dense disparity map from the two frontal images. We then align a low resolution 2D mesh model to the selected features, adjust some of its vertices along the profile line using the profile view, increase its triangular vertices to a higher resolution, and re-project them back on the frontal image. Using the coordinates of the re-projected vertices and their corresponding disparities, we capture and compute the 3D facial shape variations using stereo vision. The final result is a deformed 3D model specific to a given subject's face. Application of the model in 3D face recognition validates the algorithm and shows a promising 98 % recognition rate.

AB - We present an automatic disparity-based approach for 3D face modeling, from two frontal and one profile view stereo images, for 3D face recognition applications. Once the images are captured, the algorithm starts by extracting selected 2D facial features from one of the frontal views and computes a dense disparity map from the two frontal images. We then align a low resolution 2D mesh model to the selected features, adjust some of its vertices along the profile line using the profile view, increase its triangular vertices to a higher resolution, and re-project them back on the frontal image. Using the coordinates of the re-projected vertices and their corresponding disparities, we capture and compute the 3D facial shape variations using stereo vision. The final result is a deformed 3D model specific to a given subject's face. Application of the model in 3D face recognition validates the algorithm and shows a promising 98 % recognition rate.

KW - 3D face modeling

KW - Face recognition

UR - http://www.scopus.com/inward/record.url?scp=78649897866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649897866&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2006.312416

DO - 10.1109/ICIP.2006.312416

M3 - Conference contribution

AN - SCOPUS:78649897866

SN - 1424404819

SN - 9781424404810

SP - 657

EP - 660

BT - Proceedings - International Conference on Image Processing, ICIP

ER -