Direct extraction and fusion of image pixel features for face identity verification

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

1 Citation (Scopus)

Abstract

In this paper, we propose to adopt an entry-wise Hadamard-Schur (HS) product to extract facial information directly from raw face image pixels. With the goal of extracting relevant pixel features from each image, four different HS projection matrices which consist of directional binary patterns are proposed. Subsequently, the match score outputs from these four HS projections are fused via a total error rate minimization for performance enhancement. Our empirical experiments show encouraging performance in terms of verification accuracy.

Original languageEnglish
Title of host publicationIEEE 4th International Conference on Biometrics
Subtitle of host publicationTheory, Applications and Systems, BTAS 2010
DOIs
Publication statusPublished - 2010 Dec 27
Event4th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010 - Washington, DC, United States
Duration: 2010 Sep 272010 Sep 29

Other

Other4th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010
CountryUnited States
CityWashington, DC
Period10/9/2710/9/29

Fingerprint

Fusion
Fusion reactions
Pixel
Schur Product
Pixels
Face
Projection Matrix
Hadamard Product
Error Rate
Enhancement
Projection
Binary
Output
Experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Oh, B. S., Toh, K. A., & Teoh, A. B. J. (2010). Direct extraction and fusion of image pixel features for face identity verification. In IEEE 4th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010 [5634516] https://doi.org/10.1109/BTAS.2010.5634516
Oh, Beom Seok ; Toh, Kar Ann ; Teoh, Andrew Beng Jin. / Direct extraction and fusion of image pixel features for face identity verification. IEEE 4th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010. 2010.
@inproceedings{1fb7edcf8221429f8ecc2cd3c0f50453,
title = "Direct extraction and fusion of image pixel features for face identity verification",
abstract = "In this paper, we propose to adopt an entry-wise Hadamard-Schur (HS) product to extract facial information directly from raw face image pixels. With the goal of extracting relevant pixel features from each image, four different HS projection matrices which consist of directional binary patterns are proposed. Subsequently, the match score outputs from these four HS projections are fused via a total error rate minimization for performance enhancement. Our empirical experiments show encouraging performance in terms of verification accuracy.",
author = "Oh, {Beom Seok} and Toh, {Kar Ann} and Teoh, {Andrew Beng Jin}",
year = "2010",
month = "12",
day = "27",
doi = "10.1109/BTAS.2010.5634516",
language = "English",
isbn = "9781424475803",
booktitle = "IEEE 4th International Conference on Biometrics",

}

Oh, BS, Toh, KA & Teoh, ABJ 2010, Direct extraction and fusion of image pixel features for face identity verification. in IEEE 4th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010., 5634516, 4th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010, Washington, DC, United States, 10/9/27. https://doi.org/10.1109/BTAS.2010.5634516

Direct extraction and fusion of image pixel features for face identity verification. / Oh, Beom Seok; Toh, Kar Ann; Teoh, Andrew Beng Jin.

IEEE 4th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010. 2010. 5634516.

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

TY - GEN

T1 - Direct extraction and fusion of image pixel features for face identity verification

AU - Oh, Beom Seok

AU - Toh, Kar Ann

AU - Teoh, Andrew Beng Jin

PY - 2010/12/27

Y1 - 2010/12/27

N2 - In this paper, we propose to adopt an entry-wise Hadamard-Schur (HS) product to extract facial information directly from raw face image pixels. With the goal of extracting relevant pixel features from each image, four different HS projection matrices which consist of directional binary patterns are proposed. Subsequently, the match score outputs from these four HS projections are fused via a total error rate minimization for performance enhancement. Our empirical experiments show encouraging performance in terms of verification accuracy.

AB - In this paper, we propose to adopt an entry-wise Hadamard-Schur (HS) product to extract facial information directly from raw face image pixels. With the goal of extracting relevant pixel features from each image, four different HS projection matrices which consist of directional binary patterns are proposed. Subsequently, the match score outputs from these four HS projections are fused via a total error rate minimization for performance enhancement. Our empirical experiments show encouraging performance in terms of verification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=78650376421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650376421&partnerID=8YFLogxK

U2 - 10.1109/BTAS.2010.5634516

DO - 10.1109/BTAS.2010.5634516

M3 - Conference contribution

SN - 9781424475803

BT - IEEE 4th International Conference on Biometrics

ER -

Oh BS, Toh KA, Teoh ABJ. Direct extraction and fusion of image pixel features for face identity verification. In IEEE 4th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2010. 2010. 5634516 https://doi.org/10.1109/BTAS.2010.5634516