Face identity verification based on sinusoidal projection

Beom Seok Oh, Kar Ann Toh

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

2 Citations (Scopus)

Abstract

This paper proposes a technique for face feature extraction using sinusoidal projection. Essentially, the technique uses a projection matrix, which is formed by stacking vectors with sinusoidal values at different frequencies, to directly multiply with raw image matrix for weighted feature extraction. Orthogonality among vectors within the sinusoidal projection matrix is observed when the frequencies are chosen as multiples of the fundamental frequency. The proposed technique shows promising verification performance on three face databases.

Original languageEnglish
Title of host publicationProceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages71-76
Number of pages6
DOIs
Publication statusPublished - 2013 Dec 1
Event3rd IEEE International Workshop/Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - Singapore, Singapore
Duration: 2013 Apr 162013 Apr 19

Other

Other3rd IEEE International Workshop/Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013
CountrySingapore
CitySingapore
Period13/4/1613/4/19

Fingerprint

Databases
Feature extraction

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Artificial Intelligence
  • Computational Theory and Mathematics

Cite this

Oh, B. S., & Toh, K. A. (2013). Face identity verification based on sinusoidal projection. In Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 71-76). [6607917] https://doi.org/10.1109/CIBIM.2013.6607917
Oh, Beom Seok ; Toh, Kar Ann. / Face identity verification based on sinusoidal projection. Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 71-76
@inproceedings{d0ace160eeaa4fd98c5885e434809ee5,
title = "Face identity verification based on sinusoidal projection",
abstract = "This paper proposes a technique for face feature extraction using sinusoidal projection. Essentially, the technique uses a projection matrix, which is formed by stacking vectors with sinusoidal values at different frequencies, to directly multiply with raw image matrix for weighted feature extraction. Orthogonality among vectors within the sinusoidal projection matrix is observed when the frequencies are chosen as multiples of the fundamental frequency. The proposed technique shows promising verification performance on three face databases.",
author = "Oh, {Beom Seok} and Toh, {Kar Ann}",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/CIBIM.2013.6607917",
language = "English",
isbn = "9781467358798",
pages = "71--76",
booktitle = "Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

}

Oh, BS & Toh, KA 2013, Face identity verification based on sinusoidal projection. in Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6607917, pp. 71-76, 3rd IEEE International Workshop/Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013, Singapore, Singapore, 13/4/16. https://doi.org/10.1109/CIBIM.2013.6607917

Face identity verification based on sinusoidal projection. / Oh, Beom Seok; Toh, Kar Ann.

Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 71-76 6607917.

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

TY - GEN

T1 - Face identity verification based on sinusoidal projection

AU - Oh, Beom Seok

AU - Toh, Kar Ann

PY - 2013/12/1

Y1 - 2013/12/1

N2 - This paper proposes a technique for face feature extraction using sinusoidal projection. Essentially, the technique uses a projection matrix, which is formed by stacking vectors with sinusoidal values at different frequencies, to directly multiply with raw image matrix for weighted feature extraction. Orthogonality among vectors within the sinusoidal projection matrix is observed when the frequencies are chosen as multiples of the fundamental frequency. The proposed technique shows promising verification performance on three face databases.

AB - This paper proposes a technique for face feature extraction using sinusoidal projection. Essentially, the technique uses a projection matrix, which is formed by stacking vectors with sinusoidal values at different frequencies, to directly multiply with raw image matrix for weighted feature extraction. Orthogonality among vectors within the sinusoidal projection matrix is observed when the frequencies are chosen as multiples of the fundamental frequency. The proposed technique shows promising verification performance on three face databases.

UR - http://www.scopus.com/inward/record.url?scp=84891505523&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891505523&partnerID=8YFLogxK

U2 - 10.1109/CIBIM.2013.6607917

DO - 10.1109/CIBIM.2013.6607917

M3 - Conference contribution

SN - 9781467358798

SP - 71

EP - 76

BT - Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

ER -

Oh BS, Toh KA. Face identity verification based on sinusoidal projection. In Proceedings of the IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 71-76. 6607917 https://doi.org/10.1109/CIBIM.2013.6607917