Discriminant correlation analysis for feature level fusion with application to multimodal biometrics

M. Haghighat, Mohamed Abdel-Mottaleb, W. Alhalabi

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

22 Citations (Scopus)

Abstract

In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes. Our proposed method can be used in pattern recognition applications for fusing features extracted from multiple modalities or combining different feature vectors extracted from a single modality. It is noteworthy that DCA is the first technique that considers class structure in feature fusion. Moreover, it has a very low computational complexity and it can be employed in realtime applications. Multiple sets of experiments performed on various biometric databases show the effectiveness of our proposed method, which outperforms other state-of-the-art approaches.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1866-1870
Number of pages5
Volume2016-May
ISBN (Electronic)9781479999880
DOIs
StatePublished - May 18 2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: Mar 20 2016Mar 25 2016

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
CountryChina
CityShanghai
Period3/20/163/25/16

Fingerprint

Biometrics
Fusion reactions
Pattern recognition
Computational complexity
Experiments

Keywords

  • class structure
  • correlation analysis
  • feature level fusion
  • multimodal biometric identification

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Haghighat, M., Abdel-Mottaleb, M., & Alhalabi, W. (2016). Discriminant correlation analysis for feature level fusion with application to multimodal biometrics. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 1866-1870). [7472000] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7472000

Discriminant correlation analysis for feature level fusion with application to multimodal biometrics. / Haghighat, M.; Abdel-Mottaleb, Mohamed; Alhalabi, W.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 1866-1870 7472000.

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

Haghighat, M, Abdel-Mottaleb, M & Alhalabi, W 2016, Discriminant correlation analysis for feature level fusion with application to multimodal biometrics. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7472000, Institute of Electrical and Electronics Engineers Inc., pp. 1866-1870, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 3/20/16. https://doi.org/10.1109/ICASSP.2016.7472000
Haghighat M, Abdel-Mottaleb M, Alhalabi W. Discriminant correlation analysis for feature level fusion with application to multimodal biometrics. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1866-1870. 7472000 https://doi.org/10.1109/ICASSP.2016.7472000
Haghighat, M. ; Abdel-Mottaleb, Mohamed ; Alhalabi, W. / Discriminant correlation analysis for feature level fusion with application to multimodal biometrics. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1866-1870
@inproceedings{c8472cbeb2724235be67e831a077976c,
title = "Discriminant correlation analysis for feature level fusion with application to multimodal biometrics",
abstract = "In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes. Our proposed method can be used in pattern recognition applications for fusing features extracted from multiple modalities or combining different feature vectors extracted from a single modality. It is noteworthy that DCA is the first technique that considers class structure in feature fusion. Moreover, it has a very low computational complexity and it can be employed in realtime applications. Multiple sets of experiments performed on various biometric databases show the effectiveness of our proposed method, which outperforms other state-of-the-art approaches.",
keywords = "class structure, correlation analysis, feature level fusion, multimodal biometric identification",
author = "M. Haghighat and Mohamed Abdel-Mottaleb and W. Alhalabi",
year = "2016",
month = "5",
day = "18",
doi = "10.1109/ICASSP.2016.7472000",
language = "English (US)",
volume = "2016-May",
pages = "1866--1870",
booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Discriminant correlation analysis for feature level fusion with application to multimodal biometrics

AU - Haghighat, M.

AU - Abdel-Mottaleb, Mohamed

AU - Alhalabi, W.

PY - 2016/5/18

Y1 - 2016/5/18

N2 - In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes. Our proposed method can be used in pattern recognition applications for fusing features extracted from multiple modalities or combining different feature vectors extracted from a single modality. It is noteworthy that DCA is the first technique that considers class structure in feature fusion. Moreover, it has a very low computational complexity and it can be employed in realtime applications. Multiple sets of experiments performed on various biometric databases show the effectiveness of our proposed method, which outperforms other state-of-the-art approaches.

AB - In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes. Our proposed method can be used in pattern recognition applications for fusing features extracted from multiple modalities or combining different feature vectors extracted from a single modality. It is noteworthy that DCA is the first technique that considers class structure in feature fusion. Moreover, it has a very low computational complexity and it can be employed in realtime applications. Multiple sets of experiments performed on various biometric databases show the effectiveness of our proposed method, which outperforms other state-of-the-art approaches.

KW - class structure

KW - correlation analysis

KW - feature level fusion

KW - multimodal biometric identification

UR - http://www.scopus.com/inward/record.url?scp=84973377105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973377105&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7472000

DO - 10.1109/ICASSP.2016.7472000

M3 - Conference contribution

VL - 2016-May

SP - 1866

EP - 1870

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -