Incremental face recognition for large-scale social network services

Kwontaeg Choi, Kar Ann Toh, Hyeran Byun

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Due to the rapid growth of social network services such as Facebook and Twitter, incorporation of face recognition in these large-scale web services is attracting much attention in both academia and industry. The major problem in such applications is to deal efficiently with the growing number of samples as well as local appearance variations caused by diverse environments for the millions of users over time. In this paper, we focus on developing an incremental face recognition method for Twitter application. Particularly, a data-independent feature extraction method is proposed via binarization of a Gabor filter. Subsequently, the dimension of our Gabor representation is reduced considering various orientations at different grid positions. Finally, an incremental neural network is applied to learn the reduced Gabor features. We apply our method to a novel application which notifies new photograph uploading to related users without having their ID being identified. Our extensive experiments show that the proposed algorithm significantly outperforms several incremental face recognition methods with a dramatic reduction in computational speed. This shows the suitability of the proposed method for a large-scale web service with millions of users.

Original languageEnglish
Pages (from-to)2868-2883
Number of pages16
JournalPattern Recognition
Volume45
Issue number8
DOIs
Publication statusPublished - 2012 Jan 1

Fingerprint

Face recognition
Web services
Gabor filters
Feature extraction
Neural networks
Industry
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{c00e35c675c64b289d8dd120af6a410a,
title = "Incremental face recognition for large-scale social network services",
abstract = "Due to the rapid growth of social network services such as Facebook and Twitter, incorporation of face recognition in these large-scale web services is attracting much attention in both academia and industry. The major problem in such applications is to deal efficiently with the growing number of samples as well as local appearance variations caused by diverse environments for the millions of users over time. In this paper, we focus on developing an incremental face recognition method for Twitter application. Particularly, a data-independent feature extraction method is proposed via binarization of a Gabor filter. Subsequently, the dimension of our Gabor representation is reduced considering various orientations at different grid positions. Finally, an incremental neural network is applied to learn the reduced Gabor features. We apply our method to a novel application which notifies new photograph uploading to related users without having their ID being identified. Our extensive experiments show that the proposed algorithm significantly outperforms several incremental face recognition methods with a dramatic reduction in computational speed. This shows the suitability of the proposed method for a large-scale web service with millions of users.",
author = "Kwontaeg Choi and Toh, {Kar Ann} and Hyeran Byun",
year = "2012",
month = "1",
day = "1",
doi = "10.1016/j.patcog.2012.02.002",
language = "English",
volume = "45",
pages = "2868--2883",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "8",

}

Incremental face recognition for large-scale social network services. / Choi, Kwontaeg; Toh, Kar Ann; Byun, Hyeran.

In: Pattern Recognition, Vol. 45, No. 8, 01.01.2012, p. 2868-2883.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Incremental face recognition for large-scale social network services

AU - Choi, Kwontaeg

AU - Toh, Kar Ann

AU - Byun, Hyeran

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Due to the rapid growth of social network services such as Facebook and Twitter, incorporation of face recognition in these large-scale web services is attracting much attention in both academia and industry. The major problem in such applications is to deal efficiently with the growing number of samples as well as local appearance variations caused by diverse environments for the millions of users over time. In this paper, we focus on developing an incremental face recognition method for Twitter application. Particularly, a data-independent feature extraction method is proposed via binarization of a Gabor filter. Subsequently, the dimension of our Gabor representation is reduced considering various orientations at different grid positions. Finally, an incremental neural network is applied to learn the reduced Gabor features. We apply our method to a novel application which notifies new photograph uploading to related users without having their ID being identified. Our extensive experiments show that the proposed algorithm significantly outperforms several incremental face recognition methods with a dramatic reduction in computational speed. This shows the suitability of the proposed method for a large-scale web service with millions of users.

AB - Due to the rapid growth of social network services such as Facebook and Twitter, incorporation of face recognition in these large-scale web services is attracting much attention in both academia and industry. The major problem in such applications is to deal efficiently with the growing number of samples as well as local appearance variations caused by diverse environments for the millions of users over time. In this paper, we focus on developing an incremental face recognition method for Twitter application. Particularly, a data-independent feature extraction method is proposed via binarization of a Gabor filter. Subsequently, the dimension of our Gabor representation is reduced considering various orientations at different grid positions. Finally, an incremental neural network is applied to learn the reduced Gabor features. We apply our method to a novel application which notifies new photograph uploading to related users without having their ID being identified. Our extensive experiments show that the proposed algorithm significantly outperforms several incremental face recognition methods with a dramatic reduction in computational speed. This shows the suitability of the proposed method for a large-scale web service with millions of users.

UR - http://www.scopus.com/inward/record.url?scp=84859419728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859419728&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2012.02.002

DO - 10.1016/j.patcog.2012.02.002

M3 - Article

AN - SCOPUS:84859419728

VL - 45

SP - 2868

EP - 2883

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 8

ER -