Face Verification Based on the Age Progression Rules

Kai FANG; Shuoyan LIU

doi:10.1587/transinf.2014EDL8178

Face Verification Based on the Age Progression Rules

Kai FANG, Shuoyan LIU

Full Text Views

0

Share
Cite this

Summary :

Appearance changes conform to certain rules for a same person,while for different individuals the changes are uncontrolled. Hence, this paper studies the age progression rules to tackle face verification task. The age progression rules are discovered in the difference space of facial image pairs. For this, we first represent an image pair as a matrix whose elements are the difference of a set of visual words. Thereafter, the age progression rules are trained using Support Vector Machine (SVM) based on this matrix representation. Finally, we use these rules to accomplish the face verification tasks. The proposed approach is tested on the FGnet dataset and a collection of real-world images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.5 pp.1112-1115

Publication Date: 2015/05/01

Publicized: 2015/01/26

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDL8178

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Kai FANG
China Academy of Railway Sciences
Shuoyan LIU
China Academy of Railway Sciences

Keyword

face verification, age progression rules, Bag-of-Visual-Words, difference matrix

Cite this

Copy

Kai FANG, Shuoyan LIU, "Face Verification Based on the Age Progression Rules" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 5, pp. 1112-1115, May 2015, doi: 10.1587/transinf.2014EDL8178.
Abstract: Appearance changes conform to certain rules for a same person,while for different individuals the changes are uncontrolled. Hence, this paper studies the age progression rules to tackle face verification task. The age progression rules are discovered in the difference space of facial image pairs. For this, we first represent an image pair as a matrix whose elements are the difference of a set of visual words. Thereafter, the age progression rules are trained using Support Vector Machine (SVM) based on this matrix representation. Finally, we use these rules to accomplish the face verification tasks. The proposed approach is tested on the FGnet dataset and a collection of real-world images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8178/_p

Copy

@ARTICLE{e98-d_5_1112,
author={Kai FANG, Shuoyan LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Face Verification Based on the Age Progression Rules},
year={2015},
volume={E98-D},
number={5},
pages={1112-1115},
abstract={Appearance changes conform to certain rules for a same person,while for different individuals the changes are uncontrolled. Hence, this paper studies the age progression rules to tackle face verification task. The age progression rules are discovered in the difference space of facial image pairs. For this, we first represent an image pair as a matrix whose elements are the difference of a set of visual words. Thereafter, the age progression rules are trained using Support Vector Machine (SVM) based on this matrix representation. Finally, we use these rules to accomplish the face verification tasks. The proposed approach is tested on the FGnet dataset and a collection of real-world images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity.},
keywords={},
doi={10.1587/transinf.2014EDL8178},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Face Verification Based on the Age Progression Rules
T2 - IEICE TRANSACTIONS on Information
SP - 1112
EP - 1115
AU - Kai FANG
AU - Shuoyan LIU
PY - 2015
DO - 10.1587/transinf.2014EDL8178
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2015
AB - Appearance changes conform to certain rules for a same person,while for different individuals the changes are uncontrolled. Hence, this paper studies the age progression rules to tackle face verification task. The age progression rules are discovered in the difference space of facial image pairs. For this, we first represent an image pair as a matrix whose elements are the difference of a set of visual words. Thereafter, the age progression rules are trained using Support Vector Machine (SVM) based on this matrix representation. Finally, we use these rules to accomplish the face verification tasks. The proposed approach is tested on the FGnet dataset and a collection of real-world images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity.
ER -