Multi-race age estimation based on the combination of multiple classifiers

Kazuya Ueki, Masashi Sugiyama, Yasuyuki Ihara, Mitsuhiro Fujita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A considerable amount of research has been conducted on gender and age estimation from facial images over the last few years, and state-of-the-art technology has accomplished a practical accuracy level for a homogeneous race such as Japanese or Korean. However, achieving the same accuracy level across multiple races such as Caucasian, African American, and Hispanic is still highly challenging because of the strong diversity of the growth process of each race. Furthermore, difficulty of gathering training samples uniformly over various races and age brackets makes the problem even more challenging. In this paper, we propose a novel age estimation method that can overcome the above problems. Our method combines a recently proposed machine learning technique called Least-Squares Probabilistic Classifier (LSPC) with neural networks. Through large-scale real-world age estimation experiments, we demonstrate the usefulness of our proposed method.

Original languageEnglish
Title of host publication1st Asian Conference on Pattern Recognition, ACPR 2011
Pages633-637
Number of pages5
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event1st Asian Conference on Pattern Recognition, ACPR 2011 - Beijing, China
Duration: 2011 Nov 282011 Nov 28

Other

Other1st Asian Conference on Pattern Recognition, ACPR 2011
CountryChina
CityBeijing
Period11/11/2811/11/28

Fingerprint

Classifiers
Learning systems
Neural networks
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ueki, K., Sugiyama, M., Ihara, Y., & Fujita, M. (2011). Multi-race age estimation based on the combination of multiple classifiers. In 1st Asian Conference on Pattern Recognition, ACPR 2011 (pp. 633-637). [6166681] https://doi.org/10.1109/ACPR.2011.6166681

Multi-race age estimation based on the combination of multiple classifiers. / Ueki, Kazuya; Sugiyama, Masashi; Ihara, Yasuyuki; Fujita, Mitsuhiro.

1st Asian Conference on Pattern Recognition, ACPR 2011. 2011. p. 633-637 6166681.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ueki, K, Sugiyama, M, Ihara, Y & Fujita, M 2011, Multi-race age estimation based on the combination of multiple classifiers. in 1st Asian Conference on Pattern Recognition, ACPR 2011., 6166681, pp. 633-637, 1st Asian Conference on Pattern Recognition, ACPR 2011, Beijing, China, 11/11/28. https://doi.org/10.1109/ACPR.2011.6166681
Ueki K, Sugiyama M, Ihara Y, Fujita M. Multi-race age estimation based on the combination of multiple classifiers. In 1st Asian Conference on Pattern Recognition, ACPR 2011. 2011. p. 633-637. 6166681 https://doi.org/10.1109/ACPR.2011.6166681
Ueki, Kazuya ; Sugiyama, Masashi ; Ihara, Yasuyuki ; Fujita, Mitsuhiro. / Multi-race age estimation based on the combination of multiple classifiers. 1st Asian Conference on Pattern Recognition, ACPR 2011. 2011. pp. 633-637
@inproceedings{d711c65c32cf43318f115628fb963d62,
title = "Multi-race age estimation based on the combination of multiple classifiers",
abstract = "A considerable amount of research has been conducted on gender and age estimation from facial images over the last few years, and state-of-the-art technology has accomplished a practical accuracy level for a homogeneous race such as Japanese or Korean. However, achieving the same accuracy level across multiple races such as Caucasian, African American, and Hispanic is still highly challenging because of the strong diversity of the growth process of each race. Furthermore, difficulty of gathering training samples uniformly over various races and age brackets makes the problem even more challenging. In this paper, we propose a novel age estimation method that can overcome the above problems. Our method combines a recently proposed machine learning technique called Least-Squares Probabilistic Classifier (LSPC) with neural networks. Through large-scale real-world age estimation experiments, we demonstrate the usefulness of our proposed method.",
author = "Kazuya Ueki and Masashi Sugiyama and Yasuyuki Ihara and Mitsuhiro Fujita",
year = "2011",
doi = "10.1109/ACPR.2011.6166681",
language = "English",
isbn = "9781457701221",
pages = "633--637",
booktitle = "1st Asian Conference on Pattern Recognition, ACPR 2011",

}

TY - GEN

T1 - Multi-race age estimation based on the combination of multiple classifiers

AU - Ueki, Kazuya

AU - Sugiyama, Masashi

AU - Ihara, Yasuyuki

AU - Fujita, Mitsuhiro

PY - 2011

Y1 - 2011

N2 - A considerable amount of research has been conducted on gender and age estimation from facial images over the last few years, and state-of-the-art technology has accomplished a practical accuracy level for a homogeneous race such as Japanese or Korean. However, achieving the same accuracy level across multiple races such as Caucasian, African American, and Hispanic is still highly challenging because of the strong diversity of the growth process of each race. Furthermore, difficulty of gathering training samples uniformly over various races and age brackets makes the problem even more challenging. In this paper, we propose a novel age estimation method that can overcome the above problems. Our method combines a recently proposed machine learning technique called Least-Squares Probabilistic Classifier (LSPC) with neural networks. Through large-scale real-world age estimation experiments, we demonstrate the usefulness of our proposed method.

AB - A considerable amount of research has been conducted on gender and age estimation from facial images over the last few years, and state-of-the-art technology has accomplished a practical accuracy level for a homogeneous race such as Japanese or Korean. However, achieving the same accuracy level across multiple races such as Caucasian, African American, and Hispanic is still highly challenging because of the strong diversity of the growth process of each race. Furthermore, difficulty of gathering training samples uniformly over various races and age brackets makes the problem even more challenging. In this paper, we propose a novel age estimation method that can overcome the above problems. Our method combines a recently proposed machine learning technique called Least-Squares Probabilistic Classifier (LSPC) with neural networks. Through large-scale real-world age estimation experiments, we demonstrate the usefulness of our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84862883491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862883491&partnerID=8YFLogxK

U2 - 10.1109/ACPR.2011.6166681

DO - 10.1109/ACPR.2011.6166681

M3 - Conference contribution

AN - SCOPUS:84862883491

SN - 9781457701221

SP - 633

EP - 637

BT - 1st Asian Conference on Pattern Recognition, ACPR 2011

ER -