A robust 3D face recognition algorithm using passive stereo vision

Akihiro Hayasaka; Koichi Ito; Takafumi Aoki; Hiroshi Nakajima; Koji Kobayashi

doi:10.1587/transfun.E92.A.1047

A robust 3D face recognition algorithm using passive stereo vision

Akihiro Hayasaka, Koichi Ito, Takafumi Aoki, Hiroshi Nakajima, Koji Kobayashi

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

Abstract

The recognition performance of the conventional 3D face recognition algorithm using ICP (Iterative Closest Point) is degraded for the 3D face data with expression changes. Addressing this problem, we consider the use of the expression-invariant local regions of a face. We find the expression-invariant regions through the distance analysis between 3D face data with the neutral expression and smile, and propose a robust 3D face recognition algorithm using passive stereo vision. We demonstrate efficient recognition performance of the proposed algorithm compared with the conventional ICP-based algorithm through the experiment using a stereo face image database which includes the face images with expression changes.

Original language	English
Pages (from-to)	1047-1055
Number of pages	9
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E92-A
Issue number	4
DOIs	https://doi.org/10.1587/transfun.E92.A.1047
Publication status	Published - 2009

Keywords

3D face
Biometrics
Face recognition
Facial expression
Phaseonly correlation

ASJC Scopus subject areas

Signal Processing
Computer Graphics and Computer-Aided Design
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1587/transfun.E92.A.1047

Cite this

@article{3b309d7798db4480a68341eec4fcfd53,

title = "A robust 3D face recognition algorithm using passive stereo vision",

abstract = "The recognition performance of the conventional 3D face recognition algorithm using ICP (Iterative Closest Point) is degraded for the 3D face data with expression changes. Addressing this problem, we consider the use of the expression-invariant local regions of a face. We find the expression-invariant regions through the distance analysis between 3D face data with the neutral expression and smile, and propose a robust 3D face recognition algorithm using passive stereo vision. We demonstrate efficient recognition performance of the proposed algorithm compared with the conventional ICP-based algorithm through the experiment using a stereo face image database which includes the face images with expression changes.",

keywords = "3D face, Biometrics, Face recognition, Facial expression, Phaseonly correlation",

author = "Akihiro Hayasaka and Koichi Ito and Takafumi Aoki and Hiroshi Nakajima and Koji Kobayashi",

year = "2009",

doi = "10.1587/transfun.E92.A.1047",

language = "English",

volume = "E92-A",

pages = "1047--1055",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "4",

}

TY - JOUR

T1 - A robust 3D face recognition algorithm using passive stereo vision

AU - Hayasaka, Akihiro

AU - Ito, Koichi

AU - Aoki, Takafumi

AU - Nakajima, Hiroshi

AU - Kobayashi, Koji

PY - 2009

Y1 - 2009

N2 - The recognition performance of the conventional 3D face recognition algorithm using ICP (Iterative Closest Point) is degraded for the 3D face data with expression changes. Addressing this problem, we consider the use of the expression-invariant local regions of a face. We find the expression-invariant regions through the distance analysis between 3D face data with the neutral expression and smile, and propose a robust 3D face recognition algorithm using passive stereo vision. We demonstrate efficient recognition performance of the proposed algorithm compared with the conventional ICP-based algorithm through the experiment using a stereo face image database which includes the face images with expression changes.

AB - The recognition performance of the conventional 3D face recognition algorithm using ICP (Iterative Closest Point) is degraded for the 3D face data with expression changes. Addressing this problem, we consider the use of the expression-invariant local regions of a face. We find the expression-invariant regions through the distance analysis between 3D face data with the neutral expression and smile, and propose a robust 3D face recognition algorithm using passive stereo vision. We demonstrate efficient recognition performance of the proposed algorithm compared with the conventional ICP-based algorithm through the experiment using a stereo face image database which includes the face images with expression changes.

KW - 3D face

KW - Biometrics

KW - Face recognition

KW - Facial expression

KW - Phaseonly correlation

UR - http://www.scopus.com/inward/record.url?scp=77949516065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949516065&partnerID=8YFLogxK

U2 - 10.1587/transfun.E92.A.1047

DO - 10.1587/transfun.E92.A.1047

M3 - Article

AN - SCOPUS:77949516065

SN - 0916-8508

VL - E92-A

SP - 1047

EP - 1055

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 4

ER -

A robust 3D face recognition algorithm using passive stereo vision

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this