Automatic extraction of facial features from frontal and profile views and their 3D computations

A. Nasser Ansari, Mohamed Abdel-Mottaleb

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

Abstract

We present an algorithm for estimating the coordinates of 3D facial features from frontal and profile view images of the face. The algorithm starts by automatically localizing the 2D facial features in a frontal view image, which is then used as the basis for locating the corresponding 2D facial features in the profile view image. The 3D coordinates are computed from corresponding facial feature's coordinates in both images based on an orthogonal stereo camera set up and perspective projection. Applications to 3D generic face modeling show promising results.

Original languageEnglish (US)
Title of host publicationSixth IASTED International Conference on Signal and Image Processing
EditorsM.H. Hamza
Pages128-133
Number of pages6
StatePublished - Dec 27 2004
EventSixth IASTED International Conference on Signal and Image Processing - Honolulu, HI, United States
Duration: Aug 23 2004Aug 25 2004

Publication series

NameSixth IASTED International Conference on Signal and Image Processing

Other

OtherSixth IASTED International Conference on Signal and Image Processing
CountryUnited States
CityHonolulu, HI
Period8/23/048/25/04

Keywords

  • 3D face modeling
  • Facial analysis
  • Facial features extraction

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Automatic extraction of facial features from frontal and profile views and their 3D computations'. Together they form a unique fingerprint.

Cite this