Segmented face image verification for age-invariant face recognition

Yuta Somada, Wataru Oyama, Tetsushi Wakabayashi

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

Abstract

Face recognition has several problems to improve its performance. In particular, aging causes facial appearance variation so that it is the most difficult problem to handle. We propose a face recognition method that is robust against aging. The proposed method employs segmentation verification of frontal face images that consists of the following three steps. (1) Face image segmentation generates three regional subimages from the input face image. (2) A matching score is calculated using gradient features from a pair consisting of the input image and a registered image for each of the three generated subimages and original (whole face) image. We obtain four matching scores. (3) The verifying classifier evaluates the matching score vector and predicts the a posteriori probability that two matching images belong to the same person. The results of an experimental evaluation with the FGNET datasets clarify the effectiveness of the proposed method for age invariant face recognition.

Original languageEnglish
Title of host publication2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
Volume2018-January
ISBN (Electronic)9781538610220
DOIs
Publication statusPublished - Apr 16 2018
Externally publishedYes
Event6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017 - Himeji, Japan
Duration: Sep 1 2017Sep 3 2017

Other

Other6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017
CountryJapan
CityHimeji
Period9/1/179/3/17

Fingerprint

Face recognition
Aging of materials
Image matching
Image segmentation
Classifiers
Facial Recognition

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Biomedical Engineering
  • Media Technology
  • Health Informatics

Cite this

Somada, Y., Oyama, W., & Wakabayashi, T. (2018). Segmented face image verification for age-invariant face recognition. In 2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017 (Vol. 2018-January, pp. 1-4). [8338582] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIEV.2017.8338582

Segmented face image verification for age-invariant face recognition. / Somada, Yuta; Oyama, Wataru; Wakabayashi, Tetsushi.

2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-4 8338582.

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

Somada, Y, Oyama, W & Wakabayashi, T 2018, Segmented face image verification for age-invariant face recognition. in 2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017. vol. 2018-January, 8338582, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017, Himeji, Japan, 9/1/17. https://doi.org/10.1109/ICIEV.2017.8338582
Somada Y, Oyama W, Wakabayashi T. Segmented face image verification for age-invariant face recognition. In 2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-4. 8338582 https://doi.org/10.1109/ICIEV.2017.8338582
Somada, Yuta ; Oyama, Wataru ; Wakabayashi, Tetsushi. / Segmented face image verification for age-invariant face recognition. 2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-4
@inproceedings{a56435ff8b3845108e2197d68dfc661b,
title = "Segmented face image verification for age-invariant face recognition",
abstract = "Face recognition has several problems to improve its performance. In particular, aging causes facial appearance variation so that it is the most difficult problem to handle. We propose a face recognition method that is robust against aging. The proposed method employs segmentation verification of frontal face images that consists of the following three steps. (1) Face image segmentation generates three regional subimages from the input face image. (2) A matching score is calculated using gradient features from a pair consisting of the input image and a registered image for each of the three generated subimages and original (whole face) image. We obtain four matching scores. (3) The verifying classifier evaluates the matching score vector and predicts the a posteriori probability that two matching images belong to the same person. The results of an experimental evaluation with the FGNET datasets clarify the effectiveness of the proposed method for age invariant face recognition.",
author = "Yuta Somada and Wataru Oyama and Tetsushi Wakabayashi",
year = "2018",
month = "4",
day = "16",
doi = "10.1109/ICIEV.2017.8338582",
language = "English",
volume = "2018-January",
pages = "1--4",
booktitle = "2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Segmented face image verification for age-invariant face recognition

AU - Somada, Yuta

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

PY - 2018/4/16

Y1 - 2018/4/16

N2 - Face recognition has several problems to improve its performance. In particular, aging causes facial appearance variation so that it is the most difficult problem to handle. We propose a face recognition method that is robust against aging. The proposed method employs segmentation verification of frontal face images that consists of the following three steps. (1) Face image segmentation generates three regional subimages from the input face image. (2) A matching score is calculated using gradient features from a pair consisting of the input image and a registered image for each of the three generated subimages and original (whole face) image. We obtain four matching scores. (3) The verifying classifier evaluates the matching score vector and predicts the a posteriori probability that two matching images belong to the same person. The results of an experimental evaluation with the FGNET datasets clarify the effectiveness of the proposed method for age invariant face recognition.

AB - Face recognition has several problems to improve its performance. In particular, aging causes facial appearance variation so that it is the most difficult problem to handle. We propose a face recognition method that is robust against aging. The proposed method employs segmentation verification of frontal face images that consists of the following three steps. (1) Face image segmentation generates three regional subimages from the input face image. (2) A matching score is calculated using gradient features from a pair consisting of the input image and a registered image for each of the three generated subimages and original (whole face) image. We obtain four matching scores. (3) The verifying classifier evaluates the matching score vector and predicts the a posteriori probability that two matching images belong to the same person. The results of an experimental evaluation with the FGNET datasets clarify the effectiveness of the proposed method for age invariant face recognition.

UR - http://www.scopus.com/inward/record.url?scp=85051121362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051121362&partnerID=8YFLogxK

U2 - 10.1109/ICIEV.2017.8338582

DO - 10.1109/ICIEV.2017.8338582

M3 - Conference contribution

AN - SCOPUS:85051121362

VL - 2018-January

SP - 1

EP - 4

BT - 2017 6th International Conference on Informatics, Electronics and Vision and 2017 7th International Symposium in Computational Medical and Health Technology, ICIEV-ISCMHT 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -