Kernel Discriminant Correlation Analysis

Feature Level Fusion for Nonlinear Biometric Recognition

Yang Bai, Mohammad Haghighat, Mohamed Abdel-Mottaleb

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

Abstract

In biometric recognition, feature fusion is an important area of research due to the fact that multiple types of features contain richer and complementary information. Discriminative Correlation Analysis (DCA) is a recently proposed feature fusion method, which incorporates the class association into correlation analysis so that the features not only have the maximum intrinsic correlation between feature sets but also have class structure information. However, DCA is a linear technique, that finds a linear transformation of the original space. For highly nonlinearly distributed data, classification with nonlinear techniques works better than the linear ones. In this paper, we propose Kernel-DCA which generalizes DCA in order to handle nonlinear problems. Similar to Kernel-SVM, Kernel-DCA utilizes a kernel method to map feature sets to a high-dimensional space in which features are linearly separable. Experimental results, for the fusion of ear and face feature, using the WVU database with large variations in pose, show that Kernel-DCA achieves better results on nonlinearly distributed data than DCA and other feature fusion methods.

Original languageEnglish (US)
Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3198-3203
Number of pages6
Volume2018-August
ISBN (Electronic)9781538637883
DOIs
StatePublished - Nov 26 2018
Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
Duration: Aug 20 2018Aug 24 2018

Other

Other24th International Conference on Pattern Recognition, ICPR 2018
CountryChina
CityBeijing
Period8/20/188/24/18

Fingerprint

Biometrics
Fusion reactions
Linear transformations

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Bai, Y., Haghighat, M., & Abdel-Mottaleb, M. (2018). Kernel Discriminant Correlation Analysis: Feature Level Fusion for Nonlinear Biometric Recognition. In 2018 24th International Conference on Pattern Recognition, ICPR 2018 (Vol. 2018-August, pp. 3198-3203). [8546068] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8546068

Kernel Discriminant Correlation Analysis : Feature Level Fusion for Nonlinear Biometric Recognition. / Bai, Yang; Haghighat, Mohammad; Abdel-Mottaleb, Mohamed.

2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. p. 3198-3203 8546068.

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

Bai, Y, Haghighat, M & Abdel-Mottaleb, M 2018, Kernel Discriminant Correlation Analysis: Feature Level Fusion for Nonlinear Biometric Recognition. in 2018 24th International Conference on Pattern Recognition, ICPR 2018. vol. 2018-August, 8546068, Institute of Electrical and Electronics Engineers Inc., pp. 3198-3203, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 8/20/18. https://doi.org/10.1109/ICPR.2018.8546068
Bai Y, Haghighat M, Abdel-Mottaleb M. Kernel Discriminant Correlation Analysis: Feature Level Fusion for Nonlinear Biometric Recognition. In 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August. Institute of Electrical and Electronics Engineers Inc. 2018. p. 3198-3203. 8546068 https://doi.org/10.1109/ICPR.2018.8546068
Bai, Yang ; Haghighat, Mohammad ; Abdel-Mottaleb, Mohamed. / Kernel Discriminant Correlation Analysis : Feature Level Fusion for Nonlinear Biometric Recognition. 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. pp. 3198-3203
@inproceedings{414c1d3dfa95434487da20bf8f9eadaa,
title = "Kernel Discriminant Correlation Analysis: Feature Level Fusion for Nonlinear Biometric Recognition",
abstract = "In biometric recognition, feature fusion is an important area of research due to the fact that multiple types of features contain richer and complementary information. Discriminative Correlation Analysis (DCA) is a recently proposed feature fusion method, which incorporates the class association into correlation analysis so that the features not only have the maximum intrinsic correlation between feature sets but also have class structure information. However, DCA is a linear technique, that finds a linear transformation of the original space. For highly nonlinearly distributed data, classification with nonlinear techniques works better than the linear ones. In this paper, we propose Kernel-DCA which generalizes DCA in order to handle nonlinear problems. Similar to Kernel-SVM, Kernel-DCA utilizes a kernel method to map feature sets to a high-dimensional space in which features are linearly separable. Experimental results, for the fusion of ear and face feature, using the WVU database with large variations in pose, show that Kernel-DCA achieves better results on nonlinearly distributed data than DCA and other feature fusion methods.",
author = "Yang Bai and Mohammad Haghighat and Mohamed Abdel-Mottaleb",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICPR.2018.8546068",
language = "English (US)",
volume = "2018-August",
pages = "3198--3203",
booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Kernel Discriminant Correlation Analysis

T2 - Feature Level Fusion for Nonlinear Biometric Recognition

AU - Bai, Yang

AU - Haghighat, Mohammad

AU - Abdel-Mottaleb, Mohamed

PY - 2018/11/26

Y1 - 2018/11/26

N2 - In biometric recognition, feature fusion is an important area of research due to the fact that multiple types of features contain richer and complementary information. Discriminative Correlation Analysis (DCA) is a recently proposed feature fusion method, which incorporates the class association into correlation analysis so that the features not only have the maximum intrinsic correlation between feature sets but also have class structure information. However, DCA is a linear technique, that finds a linear transformation of the original space. For highly nonlinearly distributed data, classification with nonlinear techniques works better than the linear ones. In this paper, we propose Kernel-DCA which generalizes DCA in order to handle nonlinear problems. Similar to Kernel-SVM, Kernel-DCA utilizes a kernel method to map feature sets to a high-dimensional space in which features are linearly separable. Experimental results, for the fusion of ear and face feature, using the WVU database with large variations in pose, show that Kernel-DCA achieves better results on nonlinearly distributed data than DCA and other feature fusion methods.

AB - In biometric recognition, feature fusion is an important area of research due to the fact that multiple types of features contain richer and complementary information. Discriminative Correlation Analysis (DCA) is a recently proposed feature fusion method, which incorporates the class association into correlation analysis so that the features not only have the maximum intrinsic correlation between feature sets but also have class structure information. However, DCA is a linear technique, that finds a linear transformation of the original space. For highly nonlinearly distributed data, classification with nonlinear techniques works better than the linear ones. In this paper, we propose Kernel-DCA which generalizes DCA in order to handle nonlinear problems. Similar to Kernel-SVM, Kernel-DCA utilizes a kernel method to map feature sets to a high-dimensional space in which features are linearly separable. Experimental results, for the fusion of ear and face feature, using the WVU database with large variations in pose, show that Kernel-DCA achieves better results on nonlinearly distributed data than DCA and other feature fusion methods.

UR - http://www.scopus.com/inward/record.url?scp=85059782576&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059782576&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2018.8546068

DO - 10.1109/ICPR.2018.8546068

M3 - Conference contribution

VL - 2018-August

SP - 3198

EP - 3203

BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -