A 3D head pose estimation for face recognition

Hwanjong Song, Ukil Yang, Jaihie Kim, Kwanghoon Sohn

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

1 Citation (Scopus)

Abstract

This paper presents a three-dimensional (3D) head pose estimation algorithm for robust face recognition. Given a 3D input image, we automatically extract several important 3D facial feature points based on the facial geometry. To estimate 3D head pose accurately, we propose an Error Compensated-SVD (EC-SVD) algorithm. We estimate the initial 3D head pose of an input image using Singular Value Decomposition (SVD) method, and then perform a pose refinement procedure in the normalized face space to compensate for the error for each axis. Experimental results show that the proposed method is capable of estimating pose accurately, therefore suitable for 3D face recognition.

Original languageEnglish
Title of host publicationProceedings of the Fifth IASTED International Conference on Signal and Image Processing
EditorsH.M. Hamza
Pages133-138
Number of pages6
Volume5
Publication statusPublished - 2003 Dec 1
EventProceedings of the Fifth IASTED International Conference on Signal and Image Processing - Honolulu, HI, United States
Duration: 2003 Aug 132003 Aug 15

Other

OtherProceedings of the Fifth IASTED International Conference on Signal and Image Processing
CountryUnited States
CityHonolulu, HI
Period03/8/1303/8/15

Fingerprint

Singular value decomposition
Face recognition
decomposition
Values
mathematics
geometry
Geometry
method

All Science Journal Classification (ASJC) codes

  • Development
  • Signal Processing
  • Computer Graphics and Computer-Aided Design

Cite this

Song, H., Yang, U., Kim, J., & Sohn, K. (2003). A 3D head pose estimation for face recognition. In H. M. Hamza (Ed.), Proceedings of the Fifth IASTED International Conference on Signal and Image Processing (Vol. 5, pp. 133-138)
Song, Hwanjong ; Yang, Ukil ; Kim, Jaihie ; Sohn, Kwanghoon. / A 3D head pose estimation for face recognition. Proceedings of the Fifth IASTED International Conference on Signal and Image Processing. editor / H.M. Hamza. Vol. 5 2003. pp. 133-138
@inproceedings{274a4289b84347fcba4f266161128fb1,
title = "A 3D head pose estimation for face recognition",
abstract = "This paper presents a three-dimensional (3D) head pose estimation algorithm for robust face recognition. Given a 3D input image, we automatically extract several important 3D facial feature points based on the facial geometry. To estimate 3D head pose accurately, we propose an Error Compensated-SVD (EC-SVD) algorithm. We estimate the initial 3D head pose of an input image using Singular Value Decomposition (SVD) method, and then perform a pose refinement procedure in the normalized face space to compensate for the error for each axis. Experimental results show that the proposed method is capable of estimating pose accurately, therefore suitable for 3D face recognition.",
author = "Hwanjong Song and Ukil Yang and Jaihie Kim and Kwanghoon Sohn",
year = "2003",
month = "12",
day = "1",
language = "English",
isbn = "0889863784",
volume = "5",
pages = "133--138",
editor = "H.M. Hamza",
booktitle = "Proceedings of the Fifth IASTED International Conference on Signal and Image Processing",

}

Song, H, Yang, U, Kim, J & Sohn, K 2003, A 3D head pose estimation for face recognition. in HM Hamza (ed.), Proceedings of the Fifth IASTED International Conference on Signal and Image Processing. vol. 5, pp. 133-138, Proceedings of the Fifth IASTED International Conference on Signal and Image Processing, Honolulu, HI, United States, 03/8/13.

A 3D head pose estimation for face recognition. / Song, Hwanjong; Yang, Ukil; Kim, Jaihie; Sohn, Kwanghoon.

Proceedings of the Fifth IASTED International Conference on Signal and Image Processing. ed. / H.M. Hamza. Vol. 5 2003. p. 133-138.

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

TY - GEN

T1 - A 3D head pose estimation for face recognition

AU - Song, Hwanjong

AU - Yang, Ukil

AU - Kim, Jaihie

AU - Sohn, Kwanghoon

PY - 2003/12/1

Y1 - 2003/12/1

N2 - This paper presents a three-dimensional (3D) head pose estimation algorithm for robust face recognition. Given a 3D input image, we automatically extract several important 3D facial feature points based on the facial geometry. To estimate 3D head pose accurately, we propose an Error Compensated-SVD (EC-SVD) algorithm. We estimate the initial 3D head pose of an input image using Singular Value Decomposition (SVD) method, and then perform a pose refinement procedure in the normalized face space to compensate for the error for each axis. Experimental results show that the proposed method is capable of estimating pose accurately, therefore suitable for 3D face recognition.

AB - This paper presents a three-dimensional (3D) head pose estimation algorithm for robust face recognition. Given a 3D input image, we automatically extract several important 3D facial feature points based on the facial geometry. To estimate 3D head pose accurately, we propose an Error Compensated-SVD (EC-SVD) algorithm. We estimate the initial 3D head pose of an input image using Singular Value Decomposition (SVD) method, and then perform a pose refinement procedure in the normalized face space to compensate for the error for each axis. Experimental results show that the proposed method is capable of estimating pose accurately, therefore suitable for 3D face recognition.

UR - http://www.scopus.com/inward/record.url?scp=1542411857&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542411857&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:1542411857

SN - 0889863784

VL - 5

SP - 133

EP - 138

BT - Proceedings of the Fifth IASTED International Conference on Signal and Image Processing

A2 - Hamza, H.M.

ER -

Song H, Yang U, Kim J, Sohn K. A 3D head pose estimation for face recognition. In Hamza HM, editor, Proceedings of the Fifth IASTED International Conference on Signal and Image Processing. Vol. 5. 2003. p. 133-138