3D face recognition using depth-based features

Hyoungchul Shin, Kwanghoon Sohn

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

Abstract

A face has its structural components such as eyes, nose and mouth. Availability of depth and facial shape information of a face is one of the main advantages of three-dimensional (3D) face recognition. In order to utilize the depth information, we extract rigid facial points on facial components and their relational features. We also extract shape indexes on areas around rigid points to represent curvature information of a face. We perform face recognition by using weighted distance matching, Support Vector Machine (SVM) and Independent Component Analysis (ICA) with three different sets of features. From the experimental results, the proposed feature set performs the best compared with the other feature sets for all tested classifiers. The experimental results also show that using of both the position and the curvature features can represent a face effectively and distinctively while each of them does not provide a good discrimination power for face recognition individually.

Original languageEnglish
Title of host publicationProceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007
Pages241-246
Number of pages6
Publication statusPublished - 2007 Dec 1
Event7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007 - Palma de Mallorca, Spain
Duration: 2007 Aug 292007 Aug 31

Other

Other7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007
CountrySpain
CityPalma de Mallorca
Period07/8/2907/8/31

Fingerprint

Face recognition
Independent component analysis
Support vector machines
Classifiers
Availability

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Shin, H., & Sohn, K. (2007). 3D face recognition using depth-based features. In Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007 (pp. 241-246)
Shin, Hyoungchul ; Sohn, Kwanghoon. / 3D face recognition using depth-based features. Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007. 2007. pp. 241-246
@inproceedings{afa130ea8833416d93b077ea9216ced5,
title = "3D face recognition using depth-based features",
abstract = "A face has its structural components such as eyes, nose and mouth. Availability of depth and facial shape information of a face is one of the main advantages of three-dimensional (3D) face recognition. In order to utilize the depth information, we extract rigid facial points on facial components and their relational features. We also extract shape indexes on areas around rigid points to represent curvature information of a face. We perform face recognition by using weighted distance matching, Support Vector Machine (SVM) and Independent Component Analysis (ICA) with three different sets of features. From the experimental results, the proposed feature set performs the best compared with the other feature sets for all tested classifiers. The experimental results also show that using of both the position and the curvature features can represent a face effectively and distinctively while each of them does not provide a good discrimination power for face recognition individually.",
author = "Hyoungchul Shin and Kwanghoon Sohn",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "9780889866911",
pages = "241--246",
booktitle = "Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007",

}

Shin, H & Sohn, K 2007, 3D face recognition using depth-based features. in Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007. pp. 241-246, 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007, Palma de Mallorca, Spain, 07/8/29.

3D face recognition using depth-based features. / Shin, Hyoungchul; Sohn, Kwanghoon.

Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007. 2007. p. 241-246.

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

TY - GEN

T1 - 3D face recognition using depth-based features

AU - Shin, Hyoungchul

AU - Sohn, Kwanghoon

PY - 2007/12/1

Y1 - 2007/12/1

N2 - A face has its structural components such as eyes, nose and mouth. Availability of depth and facial shape information of a face is one of the main advantages of three-dimensional (3D) face recognition. In order to utilize the depth information, we extract rigid facial points on facial components and their relational features. We also extract shape indexes on areas around rigid points to represent curvature information of a face. We perform face recognition by using weighted distance matching, Support Vector Machine (SVM) and Independent Component Analysis (ICA) with three different sets of features. From the experimental results, the proposed feature set performs the best compared with the other feature sets for all tested classifiers. The experimental results also show that using of both the position and the curvature features can represent a face effectively and distinctively while each of them does not provide a good discrimination power for face recognition individually.

AB - A face has its structural components such as eyes, nose and mouth. Availability of depth and facial shape information of a face is one of the main advantages of three-dimensional (3D) face recognition. In order to utilize the depth information, we extract rigid facial points on facial components and their relational features. We also extract shape indexes on areas around rigid points to represent curvature information of a face. We perform face recognition by using weighted distance matching, Support Vector Machine (SVM) and Independent Component Analysis (ICA) with three different sets of features. From the experimental results, the proposed feature set performs the best compared with the other feature sets for all tested classifiers. The experimental results also show that using of both the position and the curvature features can represent a face effectively and distinctively while each of them does not provide a good discrimination power for face recognition individually.

UR - http://www.scopus.com/inward/record.url?scp=56549083494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56549083494&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780889866911

SP - 241

EP - 246

BT - Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007

ER -

Shin H, Sohn K. 3D face recognition using depth-based features. In Proceedings of the 7th IASTED International Conference on Visualization, Imaging, and Image Processing, VIIP 2007. 2007. p. 241-246