Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition

A. Nasser Ansari, Mohamed Abdel-Mottaleb

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

We present a fully automated algorithm for facial feature extraction and 3D face modeling from a pair of orthogonal frontal and profile view images of a person's face taken by calibrated cameras. The algorithm starts by automatically extracting corresponding 2D landmark facial features from both view images, then compute their 3D coordinates. Further, we estimate the coordinates of the features that are hidden in the profile view based on the visible features extracted in the two orthogonal face images. The 3D coordinates of the selected feature points obtained from the images are used first to align, then to locally deform the corresponding facial vertices of the generic 3D model. Preliminary experiments to assess the applicability of the resulted models for face recognition show encouraging results.

Original languageEnglish
Pages (from-to)2549-2563
Number of pages15
JournalPattern Recognition
Volume38
Issue number12
DOIs
StatePublished - Dec 1 2005

Fingerprint

Face recognition
Feature extraction
Cameras
Experiments

Keywords

  • 3D face modeling
  • Face recognition
  • Facial analysis
  • Feature extraction

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition. / Ansari, A. Nasser; Abdel-Mottaleb, Mohamed.

In: Pattern Recognition, Vol. 38, No. 12, 01.12.2005, p. 2549-2563.

Research output: Contribution to journalArticle

@article{c232d51a5f4444ffa5d86906dd9b6311,
title = "Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition",
abstract = "We present a fully automated algorithm for facial feature extraction and 3D face modeling from a pair of orthogonal frontal and profile view images of a person's face taken by calibrated cameras. The algorithm starts by automatically extracting corresponding 2D landmark facial features from both view images, then compute their 3D coordinates. Further, we estimate the coordinates of the features that are hidden in the profile view based on the visible features extracted in the two orthogonal face images. The 3D coordinates of the selected feature points obtained from the images are used first to align, then to locally deform the corresponding facial vertices of the generic 3D model. Preliminary experiments to assess the applicability of the resulted models for face recognition show encouraging results.",
keywords = "3D face modeling, Face recognition, Facial analysis, Feature extraction",
author = "Ansari, {A. Nasser} and Mohamed Abdel-Mottaleb",
year = "2005",
month = "12",
day = "1",
doi = "10.1016/j.patcog.2005.04.016",
language = "English",
volume = "38",
pages = "2549--2563",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "12",

}

TY - JOUR

T1 - Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition

AU - Ansari, A. Nasser

AU - Abdel-Mottaleb, Mohamed

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We present a fully automated algorithm for facial feature extraction and 3D face modeling from a pair of orthogonal frontal and profile view images of a person's face taken by calibrated cameras. The algorithm starts by automatically extracting corresponding 2D landmark facial features from both view images, then compute their 3D coordinates. Further, we estimate the coordinates of the features that are hidden in the profile view based on the visible features extracted in the two orthogonal face images. The 3D coordinates of the selected feature points obtained from the images are used first to align, then to locally deform the corresponding facial vertices of the generic 3D model. Preliminary experiments to assess the applicability of the resulted models for face recognition show encouraging results.

AB - We present a fully automated algorithm for facial feature extraction and 3D face modeling from a pair of orthogonal frontal and profile view images of a person's face taken by calibrated cameras. The algorithm starts by automatically extracting corresponding 2D landmark facial features from both view images, then compute their 3D coordinates. Further, we estimate the coordinates of the features that are hidden in the profile view based on the visible features extracted in the two orthogonal face images. The 3D coordinates of the selected feature points obtained from the images are used first to align, then to locally deform the corresponding facial vertices of the generic 3D model. Preliminary experiments to assess the applicability of the resulted models for face recognition show encouraging results.

KW - 3D face modeling

KW - Face recognition

KW - Facial analysis

KW - Feature extraction

UR - http://www.scopus.com/inward/record.url?scp=25144498707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=25144498707&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2005.04.016

DO - 10.1016/j.patcog.2005.04.016

M3 - Article

VL - 38

SP - 2549

EP - 2563

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 12

ER -