Random-profiles-based 3D face recognition system

Joongrock Kim, Sunjin Yu, Sang Youn Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, a noble nonintrusive three-dimensional (3D) face modeling system for random-profile-based 3D face recognition is presented. Although recent two-dimensional (2D) face recognition systems can achieve a reliable recognition rate under certain conditions, their performance is limited by internal and external changes, such as illumination and pose variation. To address these issues, 3D face recognition, which uses 3D face data, has recently received much attention. However, the performance of 3D face recognition highly depends on the precision of acquired 3D face data, while also requiring more computational power and storage capacity than 2D face recognition systems. In this paper, we present a developed nonintrusive 3D face modeling system composed of a stereo vision system and an invisible near-infrared line laser, which can be directly applied to profile-based 3D face recognition. We further propose a novel random-profile-based 3D face recognition method that is memory-efficient and pose-invariant. The experimental results demonstrate that the reconstructed 3D face data consists of more than 50 k 3D point clouds and a reliable recognition rate against pose variation.

Original languageEnglish
Pages (from-to)6279-6301
Number of pages23
JournalSensors (Switzerland)
Volume14
Issue number4
DOIs
Publication statusPublished - 2014 Mar 31

Fingerprint

Face recognition
profiles
Stereo vision
Facial Recognition
Lighting
Lasers
Infrared radiation
Data storage equipment
illumination

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Kim, Joongrock ; Yu, Sunjin ; Lee, Sang Youn. / Random-profiles-based 3D face recognition system. In: Sensors (Switzerland). 2014 ; Vol. 14, No. 4. pp. 6279-6301.
@article{44742def2ac54433afcf6fd23fde4f31,
title = "Random-profiles-based 3D face recognition system",
abstract = "In this paper, a noble nonintrusive three-dimensional (3D) face modeling system for random-profile-based 3D face recognition is presented. Although recent two-dimensional (2D) face recognition systems can achieve a reliable recognition rate under certain conditions, their performance is limited by internal and external changes, such as illumination and pose variation. To address these issues, 3D face recognition, which uses 3D face data, has recently received much attention. However, the performance of 3D face recognition highly depends on the precision of acquired 3D face data, while also requiring more computational power and storage capacity than 2D face recognition systems. In this paper, we present a developed nonintrusive 3D face modeling system composed of a stereo vision system and an invisible near-infrared line laser, which can be directly applied to profile-based 3D face recognition. We further propose a novel random-profile-based 3D face recognition method that is memory-efficient and pose-invariant. The experimental results demonstrate that the reconstructed 3D face data consists of more than 50 k 3D point clouds and a reliable recognition rate against pose variation.",
author = "Joongrock Kim and Sunjin Yu and Lee, {Sang Youn}",
year = "2014",
month = "3",
day = "31",
doi = "10.3390/s140406279",
language = "English",
volume = "14",
pages = "6279--6301",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

Random-profiles-based 3D face recognition system. / Kim, Joongrock; Yu, Sunjin; Lee, Sang Youn.

In: Sensors (Switzerland), Vol. 14, No. 4, 31.03.2014, p. 6279-6301.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Random-profiles-based 3D face recognition system

AU - Kim, Joongrock

AU - Yu, Sunjin

AU - Lee, Sang Youn

PY - 2014/3/31

Y1 - 2014/3/31

N2 - In this paper, a noble nonintrusive three-dimensional (3D) face modeling system for random-profile-based 3D face recognition is presented. Although recent two-dimensional (2D) face recognition systems can achieve a reliable recognition rate under certain conditions, their performance is limited by internal and external changes, such as illumination and pose variation. To address these issues, 3D face recognition, which uses 3D face data, has recently received much attention. However, the performance of 3D face recognition highly depends on the precision of acquired 3D face data, while also requiring more computational power and storage capacity than 2D face recognition systems. In this paper, we present a developed nonintrusive 3D face modeling system composed of a stereo vision system and an invisible near-infrared line laser, which can be directly applied to profile-based 3D face recognition. We further propose a novel random-profile-based 3D face recognition method that is memory-efficient and pose-invariant. The experimental results demonstrate that the reconstructed 3D face data consists of more than 50 k 3D point clouds and a reliable recognition rate against pose variation.

AB - In this paper, a noble nonintrusive three-dimensional (3D) face modeling system for random-profile-based 3D face recognition is presented. Although recent two-dimensional (2D) face recognition systems can achieve a reliable recognition rate under certain conditions, their performance is limited by internal and external changes, such as illumination and pose variation. To address these issues, 3D face recognition, which uses 3D face data, has recently received much attention. However, the performance of 3D face recognition highly depends on the precision of acquired 3D face data, while also requiring more computational power and storage capacity than 2D face recognition systems. In this paper, we present a developed nonintrusive 3D face modeling system composed of a stereo vision system and an invisible near-infrared line laser, which can be directly applied to profile-based 3D face recognition. We further propose a novel random-profile-based 3D face recognition method that is memory-efficient and pose-invariant. The experimental results demonstrate that the reconstructed 3D face data consists of more than 50 k 3D point clouds and a reliable recognition rate against pose variation.

UR - http://www.scopus.com/inward/record.url?scp=84897432870&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897432870&partnerID=8YFLogxK

U2 - 10.3390/s140406279

DO - 10.3390/s140406279

M3 - Article

VL - 14

SP - 6279

EP - 6301

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

ER -