Image-based age-group classification design using facial features

Yi Wen Chen; Meng Ju Han; Kai-Tai Song; Yu Lun Ho

doi:10.1109/ICSSE.2010.5551744

Image-based age-group classification design using facial features

Yi Wen Chen^*, Meng Ju Han, Kai-Tai Song, Yu Lun Ho

^*Corresponding author for this work

Department of Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Image recognition of a user plays an important role in designing intelligent and interactive behaviors for a domestic or service robot. In this paper, an image-based age-group classification method is proposed to estimate three levels of age groups, namely child, adult and the elderly. After face detection from the acquired image frame, human facial area is extracted and 52 feature points are located by using Lucas-Kanade image alignment method. These feature points and corresponding located facial area are used to build an active appearance model (AAM). After facial image warping, the texture features are sent to a support vector machine (SVM) to estimate the level of age group. In the experimental results, the average recognition rate of the proposed method is 87%. It will improve the interaction capability of robot in a friendly manner.

Original language	English
Title of host publication	2010 International Conference on System Science and Engineering, ICSSE 2010
Pages	548-552
Number of pages	5
DOIs	https://doi.org/10.1109/ICSSE.2010.5551744
State	Published - 11 Oct 2010
Event	2010 International Conference on System Science and Engineering, ICSSE 2010 - Taipei, Taiwan Duration: 1 Jul 2010 → 3 Jul 2010

Publication series

Name	2010 International Conference on System Science and Engineering, ICSSE 2010

Conference

Conference	2010 International Conference on System Science and Engineering, ICSSE 2010
Country	Taiwan
City	Taipei
Period	1/07/10 → 3/07/10

Keywords

Active appearance model
Age group estimation
Facial warping
Support vector machine

Access to Document

10.1109/ICSSE.2010.5551744

Fingerprint Dive into the research topics of 'Image-based age-group classification design using facial features'. Together they form a unique fingerprint.

Cite this

@inproceedings{2896f54ff043498683a6d13ca40c0dbb,

title = "Image-based age-group classification design using facial features",

abstract = "Image recognition of a user plays an important role in designing intelligent and interactive behaviors for a domestic or service robot. In this paper, an image-based age-group classification method is proposed to estimate three levels of age groups, namely child, adult and the elderly. After face detection from the acquired image frame, human facial area is extracted and 52 feature points are located by using Lucas-Kanade image alignment method. These feature points and corresponding located facial area are used to build an active appearance model (AAM). After facial image warping, the texture features are sent to a support vector machine (SVM) to estimate the level of age group. In the experimental results, the average recognition rate of the proposed method is 87%. It will improve the interaction capability of robot in a friendly manner.",

keywords = "Active appearance model, Age group estimation, Facial warping, Support vector machine",

author = "Chen, {Yi Wen} and Han, {Meng Ju} and Kai-Tai Song and Ho, {Yu Lun}",

year = "2010",

month = oct,

day = "11",

doi = "10.1109/ICSSE.2010.5551744",

language = "English",

isbn = "9781424464746",

series = "2010 International Conference on System Science and Engineering, ICSSE 2010",

pages = "548--552",

booktitle = "2010 International Conference on System Science and Engineering, ICSSE 2010",

note = "null ; Conference date: 01-07-2010 Through 03-07-2010",

}

Chen, YW, Han, MJ, Song, K-T & Ho, YL 2010, Image-based age-group classification design using facial features. in 2010 International Conference on System Science and Engineering, ICSSE 2010., 5551744, 2010 International Conference on System Science and Engineering, ICSSE 2010, pp. 548-552, 2010 International Conference on System Science and Engineering, ICSSE 2010, Taipei, Taiwan, 1/07/10. https://doi.org/10.1109/ICSSE.2010.5551744

Image-based age-group classification design using facial features. / Chen, Yi Wen; Han, Meng Ju; Song, Kai-Tai; Ho, Yu Lun.

2010 International Conference on System Science and Engineering, ICSSE 2010. 2010. p. 548-552 5551744 (2010 International Conference on System Science and Engineering, ICSSE 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Image-based age-group classification design using facial features

AU - Chen, Yi Wen

AU - Han, Meng Ju

AU - Song, Kai-Tai

AU - Ho, Yu Lun

PY - 2010/10/11

Y1 - 2010/10/11

N2 - Image recognition of a user plays an important role in designing intelligent and interactive behaviors for a domestic or service robot. In this paper, an image-based age-group classification method is proposed to estimate three levels of age groups, namely child, adult and the elderly. After face detection from the acquired image frame, human facial area is extracted and 52 feature points are located by using Lucas-Kanade image alignment method. These feature points and corresponding located facial area are used to build an active appearance model (AAM). After facial image warping, the texture features are sent to a support vector machine (SVM) to estimate the level of age group. In the experimental results, the average recognition rate of the proposed method is 87%. It will improve the interaction capability of robot in a friendly manner.

AB - Image recognition of a user plays an important role in designing intelligent and interactive behaviors for a domestic or service robot. In this paper, an image-based age-group classification method is proposed to estimate three levels of age groups, namely child, adult and the elderly. After face detection from the acquired image frame, human facial area is extracted and 52 feature points are located by using Lucas-Kanade image alignment method. These feature points and corresponding located facial area are used to build an active appearance model (AAM). After facial image warping, the texture features are sent to a support vector machine (SVM) to estimate the level of age group. In the experimental results, the average recognition rate of the proposed method is 87%. It will improve the interaction capability of robot in a friendly manner.

KW - Active appearance model

KW - Age group estimation

KW - Facial warping

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=77957590029&partnerID=8YFLogxK

U2 - 10.1109/ICSSE.2010.5551744

DO - 10.1109/ICSSE.2010.5551744

M3 - Conference contribution

AN - SCOPUS:77957590029

SN - 9781424464746

T3 - 2010 International Conference on System Science and Engineering, ICSSE 2010

SP - 548

EP - 552

BT - 2010 International Conference on System Science and Engineering, ICSSE 2010

Y2 - 1 July 2010 through 3 July 2010

ER -