Three-dimensional sensor-based face recognition

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

We describe a face recognition system based on two different three-dimensional (3D) sensors. We use 3D sensors to overcome the pose-variation problems that cannot be effectively solved in two-dimensional images. We acquire input data based on a structured-light system and compare it with 3D faces that are obtained from a 3D laser scanner. Owing to differences in structure between the input data and the 3D faces, we can generate the range images of the probe and stored images. For estimating the head pose of input data, we propose a novel error-compensated singular-value decomposition that geometrically estimates the rotation angle. Face recognition rates obtained with principal component analysis on various range images of 35 people in different poses show promising results.

Original languageEnglish
Pages (from-to)677-687
Number of pages11
JournalApplied Optics
Volume44
Issue number5
DOIs
Publication statusPublished - 2005 Feb 10

Fingerprint

Face recognition
sensors
Sensors
Singular value decomposition
Principal component analysis
Lasers
principal components analysis
scanners
estimating
decomposition
probes
estimates
lasers

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

@article{6477e856f75f43c597e48f9ef81a173d,
title = "Three-dimensional sensor-based face recognition",
abstract = "We describe a face recognition system based on two different three-dimensional (3D) sensors. We use 3D sensors to overcome the pose-variation problems that cannot be effectively solved in two-dimensional images. We acquire input data based on a structured-light system and compare it with 3D faces that are obtained from a 3D laser scanner. Owing to differences in structure between the input data and the 3D faces, we can generate the range images of the probe and stored images. For estimating the head pose of input data, we propose a novel error-compensated singular-value decomposition that geometrically estimates the rotation angle. Face recognition rates obtained with principal component analysis on various range images of 35 people in different poses show promising results.",
author = "Hwanjong Song and Sangyoun Lee and Jaihie Kim and Kwanghoon Sohn",
year = "2005",
month = "2",
day = "10",
doi = "10.1364/AO.44.000677",
language = "English",
volume = "44",
pages = "677--687",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "The Optical Society",
number = "5",

}

Three-dimensional sensor-based face recognition. / Song, Hwanjong; Lee, Sangyoun; Kim, Jaihie; Sohn, Kwanghoon.

In: Applied Optics, Vol. 44, No. 5, 10.02.2005, p. 677-687.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Three-dimensional sensor-based face recognition

AU - Song, Hwanjong

AU - Lee, Sangyoun

AU - Kim, Jaihie

AU - Sohn, Kwanghoon

PY - 2005/2/10

Y1 - 2005/2/10

N2 - We describe a face recognition system based on two different three-dimensional (3D) sensors. We use 3D sensors to overcome the pose-variation problems that cannot be effectively solved in two-dimensional images. We acquire input data based on a structured-light system and compare it with 3D faces that are obtained from a 3D laser scanner. Owing to differences in structure between the input data and the 3D faces, we can generate the range images of the probe and stored images. For estimating the head pose of input data, we propose a novel error-compensated singular-value decomposition that geometrically estimates the rotation angle. Face recognition rates obtained with principal component analysis on various range images of 35 people in different poses show promising results.

AB - We describe a face recognition system based on two different three-dimensional (3D) sensors. We use 3D sensors to overcome the pose-variation problems that cannot be effectively solved in two-dimensional images. We acquire input data based on a structured-light system and compare it with 3D faces that are obtained from a 3D laser scanner. Owing to differences in structure between the input data and the 3D faces, we can generate the range images of the probe and stored images. For estimating the head pose of input data, we propose a novel error-compensated singular-value decomposition that geometrically estimates the rotation angle. Face recognition rates obtained with principal component analysis on various range images of 35 people in different poses show promising results.

UR - http://www.scopus.com/inward/record.url?scp=14844333119&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=14844333119&partnerID=8YFLogxK

U2 - 10.1364/AO.44.000677

DO - 10.1364/AO.44.000677

M3 - Article

C2 - 15751849

AN - SCOPUS:14844333119

VL - 44

SP - 677

EP - 687

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 5

ER -