Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification

Ehab H. El-Shazly, Moataz M. Abdelwahab, Rin Ichiro Taniguchi

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

2 Citations (Scopus)

Abstract

In this paper, an efficient facial and facial expression recognition algorithm employing Canonical Correlation Analysis (CCA) for features fusion and classification is presented. Multiplefeaturesareextracted, transformedtodifferenttransformdomainsandfusedtogether. TwoDimensionalPrincipal Component Analysis (2DPCA) is used to maintain only the principal features representing different faces. 2DPCA also maintainsthespatialrelationbetweenadjacentpixelsimproving the overall recognition accuracy. CCA is being used for features fusion as well as classification. Experimental results on four different data sets showed that our algorithm outperform all most recent published state of the art techniques and reached 100 % recognition accuracy in most data sets.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015
EditorsKokou Yetongnon, Albert Dipanda, Richard Chbeir
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages639-644
Number of pages6
ISBN (Electronic)9781467397216
DOIs
Publication statusPublished - Feb 5 2016
Event11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015 - Bangkok, Thailand
Duration: Nov 23 2015Nov 27 2015

Publication series

NameProceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015

Other

Other11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015
CountryThailand
CityBangkok
Period11/23/1511/27/15

Fingerprint

Fusion reactions
Mathematical transformations

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Networks and Communications
  • Information Systems

Cite this

El-Shazly, E. H., Abdelwahab, M. M., & Taniguchi, R. I. (2016). Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification. In K. Yetongnon, A. Dipanda, & R. Chbeir (Eds.), Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015 (pp. 639-644). [7400630] (Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SITIS.2015.57

Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification. / El-Shazly, Ehab H.; Abdelwahab, Moataz M.; Taniguchi, Rin Ichiro.

Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015. ed. / Kokou Yetongnon; Albert Dipanda; Richard Chbeir. Institute of Electrical and Electronics Engineers Inc., 2016. p. 639-644 7400630 (Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015).

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

El-Shazly, EH, Abdelwahab, MM & Taniguchi, RI 2016, Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification. in K Yetongnon, A Dipanda & R Chbeir (eds), Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015., 7400630, Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015, Institute of Electrical and Electronics Engineers Inc., pp. 639-644, 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015, Bangkok, Thailand, 11/23/15. https://doi.org/10.1109/SITIS.2015.57
El-Shazly EH, Abdelwahab MM, Taniguchi RI. Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification. In Yetongnon K, Dipanda A, Chbeir R, editors, Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 639-644. 7400630. (Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015). https://doi.org/10.1109/SITIS.2015.57
El-Shazly, Ehab H. ; Abdelwahab, Moataz M. ; Taniguchi, Rin Ichiro. / Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification. Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015. editor / Kokou Yetongnon ; Albert Dipanda ; Richard Chbeir. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 639-644 (Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015).
@inproceedings{cd79ea85f2f7468292f778559e621d29,
title = "Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification",
abstract = "In this paper, an efficient facial and facial expression recognition algorithm employing Canonical Correlation Analysis (CCA) for features fusion and classification is presented. Multiplefeaturesareextracted, transformedtodifferenttransformdomainsandfusedtogether. TwoDimensionalPrincipal Component Analysis (2DPCA) is used to maintain only the principal features representing different faces. 2DPCA also maintainsthespatialrelationbetweenadjacentpixelsimproving the overall recognition accuracy. CCA is being used for features fusion as well as classification. Experimental results on four different data sets showed that our algorithm outperform all most recent published state of the art techniques and reached 100 {\%} recognition accuracy in most data sets.",
author = "El-Shazly, {Ehab H.} and Abdelwahab, {Moataz M.} and Taniguchi, {Rin Ichiro}",
year = "2016",
month = "2",
day = "5",
doi = "10.1109/SITIS.2015.57",
language = "English",
series = "Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "639--644",
editor = "Kokou Yetongnon and Albert Dipanda and Richard Chbeir",
booktitle = "Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015",
address = "United States",

}

TY - GEN

T1 - Efficient Facial and Facial Expression Recognition Using Canonical Correlation Analysis for Transform Domain Features Fusion and Classification

AU - El-Shazly, Ehab H.

AU - Abdelwahab, Moataz M.

AU - Taniguchi, Rin Ichiro

PY - 2016/2/5

Y1 - 2016/2/5

N2 - In this paper, an efficient facial and facial expression recognition algorithm employing Canonical Correlation Analysis (CCA) for features fusion and classification is presented. Multiplefeaturesareextracted, transformedtodifferenttransformdomainsandfusedtogether. TwoDimensionalPrincipal Component Analysis (2DPCA) is used to maintain only the principal features representing different faces. 2DPCA also maintainsthespatialrelationbetweenadjacentpixelsimproving the overall recognition accuracy. CCA is being used for features fusion as well as classification. Experimental results on four different data sets showed that our algorithm outperform all most recent published state of the art techniques and reached 100 % recognition accuracy in most data sets.

AB - In this paper, an efficient facial and facial expression recognition algorithm employing Canonical Correlation Analysis (CCA) for features fusion and classification is presented. Multiplefeaturesareextracted, transformedtodifferenttransformdomainsandfusedtogether. TwoDimensionalPrincipal Component Analysis (2DPCA) is used to maintain only the principal features representing different faces. 2DPCA also maintainsthespatialrelationbetweenadjacentpixelsimproving the overall recognition accuracy. CCA is being used for features fusion as well as classification. Experimental results on four different data sets showed that our algorithm outperform all most recent published state of the art techniques and reached 100 % recognition accuracy in most data sets.

UR - http://www.scopus.com/inward/record.url?scp=84966277128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966277128&partnerID=8YFLogxK

U2 - 10.1109/SITIS.2015.57

DO - 10.1109/SITIS.2015.57

M3 - Conference contribution

AN - SCOPUS:84966277128

T3 - Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015

SP - 639

EP - 644

BT - Proceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015

A2 - Yetongnon, Kokou

A2 - Dipanda, Albert

A2 - Chbeir, Richard

PB - Institute of Electrical and Electronics Engineers Inc.

ER -