A comparative study of local feature extraction for age estimation

Sung Eun Choi, Youn Joo Lee, Sung Joo Lee, Kang Ryoung Park, Jaihie Kim

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

23 Citations (Scopus)

Abstract

Many age estimation methods have been proposed for various applications such as Age Specific Human Computer Interaction (ASHCI) system, age simulation system and so on. Because the performance of the age estimation is greatly affected by the aging feature, the aging feature extraction from facial images is very important. The aging features used in previous works can be divided into global and local features. As global features, Active Appearance Models (AAM) was mainly used for age estimation in previous works. However, AAM is not enough to represent local features such as wrinkle and skin. Therefore, the research about local features is required. In previous works, local features were generally used to determine age group rather than detailed age, and the comparative studies about various local features extraction methods were not conducted. In this paper, the performances of sobel filter, difference image between original and smoothed image, ideal high pass filter (IHPF), gaussian high pass filter (GHPF), Haar and Daubechies discrete wavelet transform (DWT) are compared for extracting local features and detailed age estimation is performed by Support Vector Regression (SVR) on BERC and PAL aging database. The experimental results show that local features can be used for detailed age estimation and GHPF gives a better performance than other methods.

Original languageEnglish
Title of host publication11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Pages1280-1284
Number of pages5
DOIs
Publication statusPublished - 2010 Dec 1
Event11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 - Singapore, Singapore
Duration: 2010 Dec 72010 Dec 10

Publication series

Name11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

Other

Other11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
CountrySingapore
CitySingapore
Period10/12/710/12/10

Fingerprint

Feature extraction
High pass filters
Aging of materials
Discrete wavelet transforms
Human computer interaction
Skin

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Choi, S. E., Lee, Y. J., Lee, S. J., Park, K. R., & Kim, J. (2010). A comparative study of local feature extraction for age estimation. In 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 (pp. 1280-1284). [5707432] (11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010). https://doi.org/10.1109/ICARCV.2010.5707432
Choi, Sung Eun ; Lee, Youn Joo ; Lee, Sung Joo ; Park, Kang Ryoung ; Kim, Jaihie. / A comparative study of local feature extraction for age estimation. 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. 2010. pp. 1280-1284 (11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010).
@inproceedings{e0104176c59544c7a212e9ef5022068e,
title = "A comparative study of local feature extraction for age estimation",
abstract = "Many age estimation methods have been proposed for various applications such as Age Specific Human Computer Interaction (ASHCI) system, age simulation system and so on. Because the performance of the age estimation is greatly affected by the aging feature, the aging feature extraction from facial images is very important. The aging features used in previous works can be divided into global and local features. As global features, Active Appearance Models (AAM) was mainly used for age estimation in previous works. However, AAM is not enough to represent local features such as wrinkle and skin. Therefore, the research about local features is required. In previous works, local features were generally used to determine age group rather than detailed age, and the comparative studies about various local features extraction methods were not conducted. In this paper, the performances of sobel filter, difference image between original and smoothed image, ideal high pass filter (IHPF), gaussian high pass filter (GHPF), Haar and Daubechies discrete wavelet transform (DWT) are compared for extracting local features and detailed age estimation is performed by Support Vector Regression (SVR) on BERC and PAL aging database. The experimental results show that local features can be used for detailed age estimation and GHPF gives a better performance than other methods.",
author = "Choi, {Sung Eun} and Lee, {Youn Joo} and Lee, {Sung Joo} and Park, {Kang Ryoung} and Jaihie Kim",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICARCV.2010.5707432",
language = "English",
isbn = "9781424478132",
series = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",
pages = "1280--1284",
booktitle = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",

}

Choi, SE, Lee, YJ, Lee, SJ, Park, KR & Kim, J 2010, A comparative study of local feature extraction for age estimation. in 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010., 5707432, 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, pp. 1280-1284, 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, Singapore, Singapore, 10/12/7. https://doi.org/10.1109/ICARCV.2010.5707432

A comparative study of local feature extraction for age estimation. / Choi, Sung Eun; Lee, Youn Joo; Lee, Sung Joo; Park, Kang Ryoung; Kim, Jaihie.

11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. 2010. p. 1280-1284 5707432 (11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010).

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

TY - GEN

T1 - A comparative study of local feature extraction for age estimation

AU - Choi, Sung Eun

AU - Lee, Youn Joo

AU - Lee, Sung Joo

AU - Park, Kang Ryoung

AU - Kim, Jaihie

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Many age estimation methods have been proposed for various applications such as Age Specific Human Computer Interaction (ASHCI) system, age simulation system and so on. Because the performance of the age estimation is greatly affected by the aging feature, the aging feature extraction from facial images is very important. The aging features used in previous works can be divided into global and local features. As global features, Active Appearance Models (AAM) was mainly used for age estimation in previous works. However, AAM is not enough to represent local features such as wrinkle and skin. Therefore, the research about local features is required. In previous works, local features were generally used to determine age group rather than detailed age, and the comparative studies about various local features extraction methods were not conducted. In this paper, the performances of sobel filter, difference image between original and smoothed image, ideal high pass filter (IHPF), gaussian high pass filter (GHPF), Haar and Daubechies discrete wavelet transform (DWT) are compared for extracting local features and detailed age estimation is performed by Support Vector Regression (SVR) on BERC and PAL aging database. The experimental results show that local features can be used for detailed age estimation and GHPF gives a better performance than other methods.

AB - Many age estimation methods have been proposed for various applications such as Age Specific Human Computer Interaction (ASHCI) system, age simulation system and so on. Because the performance of the age estimation is greatly affected by the aging feature, the aging feature extraction from facial images is very important. The aging features used in previous works can be divided into global and local features. As global features, Active Appearance Models (AAM) was mainly used for age estimation in previous works. However, AAM is not enough to represent local features such as wrinkle and skin. Therefore, the research about local features is required. In previous works, local features were generally used to determine age group rather than detailed age, and the comparative studies about various local features extraction methods were not conducted. In this paper, the performances of sobel filter, difference image between original and smoothed image, ideal high pass filter (IHPF), gaussian high pass filter (GHPF), Haar and Daubechies discrete wavelet transform (DWT) are compared for extracting local features and detailed age estimation is performed by Support Vector Regression (SVR) on BERC and PAL aging database. The experimental results show that local features can be used for detailed age estimation and GHPF gives a better performance than other methods.

UR - http://www.scopus.com/inward/record.url?scp=79952420858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952420858&partnerID=8YFLogxK

U2 - 10.1109/ICARCV.2010.5707432

DO - 10.1109/ICARCV.2010.5707432

M3 - Conference contribution

AN - SCOPUS:79952420858

SN - 9781424478132

T3 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

SP - 1280

EP - 1284

BT - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

ER -

Choi SE, Lee YJ, Lee SJ, Park KR, Kim J. A comparative study of local feature extraction for age estimation. In 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. 2010. p. 1280-1284. 5707432. (11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010). https://doi.org/10.1109/ICARCV.2010.5707432