3D head pose-normalization using 2D and 3D interaction

Joongrock Kim; Sunjin Yu; Sangyoun Lee

doi:10.1109/ICCAS.2007.4406736

3D head pose-normalization using 2D and 3D interaction

Joongrock Kim, Sunjin Yu, Sangyoun Lee

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Pose-variation factors present a significant problem in 2D face recognition. To solve this problem, there are various approaches for a 3D face acquisition system which was able to generate multi-view images. However, this created another pose estimation problem in terms of normalizing the 3D face data. This paper presents a 3D head pose-normalization method using 2D and 3D interaction. The proposed method uses 2D information with the AAM(Active Appearance Model) and 3D information with a 3D normal vector. In order to verify the performance of the proposed method, we designed an experiment using DP(Dynamic Programming). Experimental results showed that the proposed method is robust against pose variation.

Original language	English
Title of host publication	ICCAS 2007 - International Conference on Control, Automation and Systems
Pages	2242-2245
Number of pages	4
DOIs	https://doi.org/10.1109/ICCAS.2007.4406736
Publication status	Published - 2007
Event	International Conference on Control, Automation and Systems, ICCAS 2007 - Seoul, Korea, Republic of Duration: 2007 Oct 17 → 2007 Oct 20

Publication series

Name	ICCAS 2007 - International Conference on Control, Automation and Systems

Other

Other	International Conference on Control, Automation and Systems, ICCAS 2007
Country/Territory	Korea, Republic of
City	Seoul
Period	07/10/17 → 07/10/20

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ICCAS.2007.4406736

Cite this

@inproceedings{fa2468edf3b3489ea018733bd9823dac,

title = "3D head pose-normalization using 2D and 3D interaction",

abstract = "Pose-variation factors present a significant problem in 2D face recognition. To solve this problem, there are various approaches for a 3D face acquisition system which was able to generate multi-view images. However, this created another pose estimation problem in terms of normalizing the 3D face data. This paper presents a 3D head pose-normalization method using 2D and 3D interaction. The proposed method uses 2D information with the AAM(Active Appearance Model) and 3D information with a 3D normal vector. In order to verify the performance of the proposed method, we designed an experiment using DP(Dynamic Programming). Experimental results showed that the proposed method is robust against pose variation.",

author = "Joongrock Kim and Sunjin Yu and Sangyoun Lee",

year = "2007",

doi = "10.1109/ICCAS.2007.4406736",

language = "English",

isbn = "8995003871",

series = "ICCAS 2007 - International Conference on Control, Automation and Systems",

pages = "2242--2245",

booktitle = "ICCAS 2007 - International Conference on Control, Automation and Systems",

note = "International Conference on Control, Automation and Systems, ICCAS 2007 ; Conference date: 17-10-2007 Through 20-10-2007",

}

Kim, J, Yu, S & Lee, S 2007, 3D head pose-normalization using 2D and 3D interaction. in ICCAS 2007 - International Conference on Control, Automation and Systems., 4406736, ICCAS 2007 - International Conference on Control, Automation and Systems, pp. 2242-2245, International Conference on Control, Automation and Systems, ICCAS 2007, Seoul, Korea, Republic of, 07/10/17. https://doi.org/10.1109/ICCAS.2007.4406736

TY - GEN

T1 - 3D head pose-normalization using 2D and 3D interaction

AU - Kim, Joongrock

AU - Yu, Sunjin

AU - Lee, Sangyoun

PY - 2007

Y1 - 2007

N2 - Pose-variation factors present a significant problem in 2D face recognition. To solve this problem, there are various approaches for a 3D face acquisition system which was able to generate multi-view images. However, this created another pose estimation problem in terms of normalizing the 3D face data. This paper presents a 3D head pose-normalization method using 2D and 3D interaction. The proposed method uses 2D information with the AAM(Active Appearance Model) and 3D information with a 3D normal vector. In order to verify the performance of the proposed method, we designed an experiment using DP(Dynamic Programming). Experimental results showed that the proposed method is robust against pose variation.

AB - Pose-variation factors present a significant problem in 2D face recognition. To solve this problem, there are various approaches for a 3D face acquisition system which was able to generate multi-view images. However, this created another pose estimation problem in terms of normalizing the 3D face data. This paper presents a 3D head pose-normalization method using 2D and 3D interaction. The proposed method uses 2D information with the AAM(Active Appearance Model) and 3D information with a 3D normal vector. In order to verify the performance of the proposed method, we designed an experiment using DP(Dynamic Programming). Experimental results showed that the proposed method is robust against pose variation.

UR - http://www.scopus.com/inward/record.url?scp=48349134359&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48349134359&partnerID=8YFLogxK

U2 - 10.1109/ICCAS.2007.4406736

DO - 10.1109/ICCAS.2007.4406736

M3 - Conference contribution

AN - SCOPUS:48349134359

SN - 8995003871

SN - 9788995003879

T3 - ICCAS 2007 - International Conference on Control, Automation and Systems

SP - 2242

EP - 2245

BT - ICCAS 2007 - International Conference on Control, Automation and Systems

T2 - International Conference on Control, Automation and Systems, ICCAS 2007

Y2 - 17 October 2007 through 20 October 2007

ER -

3D head pose-normalization using 2D and 3D interaction

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this