Multi-Modal Biometrics Fusion: Beyond Optimal Weighting

Kar Ann Toh, Wei Yun Yau

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

1 Citation (Scopus)

Abstract

The Multivariate polynomials model provides an effective way to describe complex nonlinear input-output relationships as it is tractable for optimization, sensitivity analysis, and prediction of confidence intervals. However, for high dimensional and high order problems, multivariate polynomial regression becomes impractical due to its prohibitive number of product terms. This is especially true for the case of a full interaction model. In this paper, we propose a reduced multivariate polynomials model to circumvent the dimensionality problem with some compromise in the approximation capability. When applied to multi-modal biometrics fusion, this model is demonstrated to improve the combined classification performance in terms of classification accuracy.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002
Pages788-792
Number of pages5
Publication statusPublished - 2002 Dec 1
EventProceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002 - Singapore, Singapore
Duration: 2002 Dec 22002 Dec 5

Publication series

NameProceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002

Other

OtherProceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002
CountrySingapore
CitySingapore
Period02/12/202/12/5

Fingerprint

Biometrics
Fusion reactions
Sensitivity analysis
Polynomials
Statistical Models

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Toh, K. A., & Yau, W. Y. (2002). Multi-Modal Biometrics Fusion: Beyond Optimal Weighting. In Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002 (pp. 788-792). (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).
Toh, Kar Ann ; Yau, Wei Yun. / Multi-Modal Biometrics Fusion : Beyond Optimal Weighting. Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. 2002. pp. 788-792 (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).
@inproceedings{6b9d7efc94694c3b988182b99132b834,
title = "Multi-Modal Biometrics Fusion: Beyond Optimal Weighting",
abstract = "The Multivariate polynomials model provides an effective way to describe complex nonlinear input-output relationships as it is tractable for optimization, sensitivity analysis, and prediction of confidence intervals. However, for high dimensional and high order problems, multivariate polynomial regression becomes impractical due to its prohibitive number of product terms. This is especially true for the case of a full interaction model. In this paper, we propose a reduced multivariate polynomials model to circumvent the dimensionality problem with some compromise in the approximation capability. When applied to multi-modal biometrics fusion, this model is demonstrated to improve the combined classification performance in terms of classification accuracy.",
author = "Toh, {Kar Ann} and Yau, {Wei Yun}",
year = "2002",
month = "12",
day = "1",
language = "English",
isbn = "9810474806",
series = "Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002",
pages = "788--792",
booktitle = "Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002",

}

Toh, KA & Yau, WY 2002, Multi-Modal Biometrics Fusion: Beyond Optimal Weighting. in Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002, pp. 788-792, Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002, Singapore, Singapore, 02/12/2.

Multi-Modal Biometrics Fusion : Beyond Optimal Weighting. / Toh, Kar Ann; Yau, Wei Yun.

Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. 2002. p. 788-792 (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).

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

TY - GEN

T1 - Multi-Modal Biometrics Fusion

T2 - Beyond Optimal Weighting

AU - Toh, Kar Ann

AU - Yau, Wei Yun

PY - 2002/12/1

Y1 - 2002/12/1

N2 - The Multivariate polynomials model provides an effective way to describe complex nonlinear input-output relationships as it is tractable for optimization, sensitivity analysis, and prediction of confidence intervals. However, for high dimensional and high order problems, multivariate polynomial regression becomes impractical due to its prohibitive number of product terms. This is especially true for the case of a full interaction model. In this paper, we propose a reduced multivariate polynomials model to circumvent the dimensionality problem with some compromise in the approximation capability. When applied to multi-modal biometrics fusion, this model is demonstrated to improve the combined classification performance in terms of classification accuracy.

AB - The Multivariate polynomials model provides an effective way to describe complex nonlinear input-output relationships as it is tractable for optimization, sensitivity analysis, and prediction of confidence intervals. However, for high dimensional and high order problems, multivariate polynomial regression becomes impractical due to its prohibitive number of product terms. This is especially true for the case of a full interaction model. In this paper, we propose a reduced multivariate polynomials model to circumvent the dimensionality problem with some compromise in the approximation capability. When applied to multi-modal biometrics fusion, this model is demonstrated to improve the combined classification performance in terms of classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=2342431919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2342431919&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:2342431919

SN - 9810474806

SN - 9789810474805

T3 - Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002

SP - 788

EP - 792

BT - Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002

ER -

Toh KA, Yau WY. Multi-Modal Biometrics Fusion: Beyond Optimal Weighting. In Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. 2002. p. 788-792. (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).