Common and Adapted Vocabularies for Face Verification

Shuoyan LIU; Kai FANG

doi:10.1587/transinf.2015EDL8117

Common and Adapted Vocabularies for Face Verification

Shuoyan LIU, Kai FANG

Full Text Views

0

Share
Cite this

Summary :

Face verification in the presence of age progression is an important problem that has not been widely addressed. Despite appearance changes for same person due to aging, they are more similar compared to facial images from different individuals. Hence, we design common and adapted vocabularies, where common vocabulary describes contents of general population and adapted vocabulary represents specific characteristics of one of image facial pairs. And the other image is characterized with a concatenation histogram of common and adapted visual words counts, termed as “age-invariant distinctive representation”. The representation describes whether the image content is best modeled by the common vocabulary or the corresponding adapted vocabulary, which is further used to accomplish the face verification. The proposed approach is tested on the FGnet dataset and a collection of real-world facial images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity at a modest computational cost.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.12 pp.2337-2340

Publication Date: 2015/12/01

Publicized: 2015/09/18

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDL8117

Type of Manuscript: LETTER

Category: Pattern Recognition

Authors

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

Keyword

face verification, bag-of-words, concatenation histogram

Cite this

Copy

Shuoyan LIU, Kai FANG, "Common and Adapted Vocabularies for Face Verification" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 12, pp. 2337-2340, December 2015, doi: 10.1587/transinf.2015EDL8117.
Abstract: Face verification in the presence of age progression is an important problem that has not been widely addressed. Despite appearance changes for same person due to aging, they are more similar compared to facial images from different individuals. Hence, we design common and adapted vocabularies, where common vocabulary describes contents of general population and adapted vocabulary represents specific characteristics of one of image facial pairs. And the other image is characterized with a concatenation histogram of common and adapted visual words counts, termed as “age-invariant distinctive representation”. The representation describes whether the image content is best modeled by the common vocabulary or the corresponding adapted vocabulary, which is further used to accomplish the face verification. The proposed approach is tested on the FGnet dataset and a collection of real-world facial images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity at a modest computational cost.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8117/_p

Copy

@ARTICLE{e98-d_12_2337,
author={Shuoyan LIU, Kai FANG, },
journal={IEICE TRANSACTIONS on Information},
title={Common and Adapted Vocabularies for Face Verification},
year={2015},
volume={E98-D},
number={12},
pages={2337-2340},
abstract={Face verification in the presence of age progression is an important problem that has not been widely addressed. Despite appearance changes for same person due to aging, they are more similar compared to facial images from different individuals. Hence, we design common and adapted vocabularies, where common vocabulary describes contents of general population and adapted vocabulary represents specific characteristics of one of image facial pairs. And the other image is characterized with a concatenation histogram of common and adapted visual words counts, termed as “age-invariant distinctive representation”. The representation describes whether the image content is best modeled by the common vocabulary or the corresponding adapted vocabulary, which is further used to accomplish the face verification. The proposed approach is tested on the FGnet dataset and a collection of real-world facial images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity at a modest computational cost.},
keywords={},
doi={10.1587/transinf.2015EDL8117},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Common and Adapted Vocabularies for Face Verification
T2 - IEICE TRANSACTIONS on Information
SP - 2337
EP - 2340
AU - Shuoyan LIU
AU - Kai FANG
PY - 2015
DO - 10.1587/transinf.2015EDL8117
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2015
AB - Face verification in the presence of age progression is an important problem that has not been widely addressed. Despite appearance changes for same person due to aging, they are more similar compared to facial images from different individuals. Hence, we design common and adapted vocabularies, where common vocabulary describes contents of general population and adapted vocabulary represents specific characteristics of one of image facial pairs. And the other image is characterized with a concatenation histogram of common and adapted visual words counts, termed as “age-invariant distinctive representation”. The representation describes whether the image content is best modeled by the common vocabulary or the corresponding adapted vocabulary, which is further used to accomplish the face verification. The proposed approach is tested on the FGnet dataset and a collection of real-world facial images from identification card. The experimental results demonstrate the effectiveness of the proposed method for verification of identity at a modest computational cost.
ER -