Lighting condition adaptation for perceived age estimation

Kazuya Ueki, Masashi Sugiyama, Yasuyuki Ihara

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Over the recent years, a great deal of effort has been made to estimate age from face images. It has been reported that age can be accurately estimated under controlled environment such as frontal faces, no expression, and static lighting conditions. However, it is not straightforward to achieve the same accuracy level in a real-world environment due to considerable variations in camera settings, facial poses, and illumination conditions. In this paper, we apply a recently proposed machine learning technique called covariate shift adaptation to alleviating lighting condition change between laboratory and practical environment. Through real-world age estimation experiments, we demonstrate the usefulness of our proposed method.

Original languageEnglish
Pages (from-to)392-395
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE94-D
Issue number2
DOIs
Publication statusPublished - 2011 Feb
Externally publishedYes

Fingerprint

Lighting
Learning systems
Cameras
Experiments

Keywords

  • Age estimation
  • Covariate shift adaptation
  • Face recognition
  • Importance-weighted regularized least-squares
  • Kullback-Leibler importance estimation procedure
  • Lighting condition change

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Lighting condition adaptation for perceived age estimation. / Ueki, Kazuya; Sugiyama, Masashi; Ihara, Yasuyuki.

In: IEICE Transactions on Information and Systems, Vol. E94-D, No. 2, 02.2011, p. 392-395.

Research output: Contribution to journalArticle

Ueki, Kazuya ; Sugiyama, Masashi ; Ihara, Yasuyuki. / Lighting condition adaptation for perceived age estimation. In: IEICE Transactions on Information and Systems. 2011 ; Vol. E94-D, No. 2. pp. 392-395.
@article{80ce5584d888418fa9c5a95efaec4117,
title = "Lighting condition adaptation for perceived age estimation",
abstract = "Over the recent years, a great deal of effort has been made to estimate age from face images. It has been reported that age can be accurately estimated under controlled environment such as frontal faces, no expression, and static lighting conditions. However, it is not straightforward to achieve the same accuracy level in a real-world environment due to considerable variations in camera settings, facial poses, and illumination conditions. In this paper, we apply a recently proposed machine learning technique called covariate shift adaptation to alleviating lighting condition change between laboratory and practical environment. Through real-world age estimation experiments, we demonstrate the usefulness of our proposed method.",
keywords = "Age estimation, Covariate shift adaptation, Face recognition, Importance-weighted regularized least-squares, Kullback-Leibler importance estimation procedure, Lighting condition change",
author = "Kazuya Ueki and Masashi Sugiyama and Yasuyuki Ihara",
year = "2011",
month = "2",
doi = "10.1587/transinf.E94.D.392",
language = "English",
volume = "E94-D",
pages = "392--395",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

TY - JOUR

T1 - Lighting condition adaptation for perceived age estimation

AU - Ueki, Kazuya

AU - Sugiyama, Masashi

AU - Ihara, Yasuyuki

PY - 2011/2

Y1 - 2011/2

N2 - Over the recent years, a great deal of effort has been made to estimate age from face images. It has been reported that age can be accurately estimated under controlled environment such as frontal faces, no expression, and static lighting conditions. However, it is not straightforward to achieve the same accuracy level in a real-world environment due to considerable variations in camera settings, facial poses, and illumination conditions. In this paper, we apply a recently proposed machine learning technique called covariate shift adaptation to alleviating lighting condition change between laboratory and practical environment. Through real-world age estimation experiments, we demonstrate the usefulness of our proposed method.

AB - Over the recent years, a great deal of effort has been made to estimate age from face images. It has been reported that age can be accurately estimated under controlled environment such as frontal faces, no expression, and static lighting conditions. However, it is not straightforward to achieve the same accuracy level in a real-world environment due to considerable variations in camera settings, facial poses, and illumination conditions. In this paper, we apply a recently proposed machine learning technique called covariate shift adaptation to alleviating lighting condition change between laboratory and practical environment. Through real-world age estimation experiments, we demonstrate the usefulness of our proposed method.

KW - Age estimation

KW - Covariate shift adaptation

KW - Face recognition

KW - Importance-weighted regularized least-squares

KW - Kullback-Leibler importance estimation procedure

KW - Lighting condition change

UR - http://www.scopus.com/inward/record.url?scp=79951485625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951485625&partnerID=8YFLogxK

U2 - 10.1587/transinf.E94.D.392

DO - 10.1587/transinf.E94.D.392

M3 - Article

AN - SCOPUS:79951485625

VL - E94-D

SP - 392

EP - 395

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 2

ER -