Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition

Sih Huei Chen, Yuan Shan Lee, Yu Sheng Hsu, Chung-Hsien Wu, Jia Ching Wang

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

1 Citation (Scopus)

Abstract

Learning a low-dimensional image representation yields effective and efficient face recognition. The use of such a representation helps to weaken the curse of dimensionality. However, the traditional facial representation method is not robust against partial occlusions or variations of expression. To solve this problem, this paper proposes a more reliable, complex-valued representation of facial image. The robust representation is based on the proposed locality-preserving complex-valued Gaussian process latent variable model (LP-CGPLVM). In the LP-CGPLVM, the Euler formula is utilized to transform original facial images into the complex domain. A proper complex GP is employed to model the mapping between the complex-valued high-dimensional data and the corresponding low-dimensional representation. Moreover, the locality-preserving constraint is taken into consideration to preserve the neighborhood data structure. The experimental results indicate that our proposed method is robust against partial occlusions and various facial expressions.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2696-2700
Number of pages5
Volume2018-April
ISBN (Print)9781538646588
DOIs
Publication statusPublished - 2018 Sep 10
Event2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada
Duration: 2018 Apr 152018 Apr 20

Other

Other2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
CountryCanada
CityCalgary
Period18-04-1518-04-20

Fingerprint

Face recognition
Data structures

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Chen, S. H., Lee, Y. S., Hsu, Y. S., Wu, C-H., & Wang, J. C. (2018). Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition. In 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings (Vol. 2018-April, pp. 2696-2700). [8462680] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2018.8462680
Chen, Sih Huei ; Lee, Yuan Shan ; Hsu, Yu Sheng ; Wu, Chung-Hsien ; Wang, Jia Ching. / Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition. 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Vol. 2018-April Institute of Electrical and Electronics Engineers Inc., 2018. pp. 2696-2700
@inproceedings{95e1ee3a2f6c4ba9b32e2c5dfb2f4247,
title = "Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition",
abstract = "Learning a low-dimensional image representation yields effective and efficient face recognition. The use of such a representation helps to weaken the curse of dimensionality. However, the traditional facial representation method is not robust against partial occlusions or variations of expression. To solve this problem, this paper proposes a more reliable, complex-valued representation of facial image. The robust representation is based on the proposed locality-preserving complex-valued Gaussian process latent variable model (LP-CGPLVM). In the LP-CGPLVM, the Euler formula is utilized to transform original facial images into the complex domain. A proper complex GP is employed to model the mapping between the complex-valued high-dimensional data and the corresponding low-dimensional representation. Moreover, the locality-preserving constraint is taken into consideration to preserve the neighborhood data structure. The experimental results indicate that our proposed method is robust against partial occlusions and various facial expressions.",
author = "Chen, {Sih Huei} and Lee, {Yuan Shan} and Hsu, {Yu Sheng} and Chung-Hsien Wu and Wang, {Jia Ching}",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/ICASSP.2018.8462680",
language = "English",
isbn = "9781538646588",
volume = "2018-April",
pages = "2696--2700",
booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Chen, SH, Lee, YS, Hsu, YS, Wu, C-H & Wang, JC 2018, Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition. in 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. vol. 2018-April, 8462680, Institute of Electrical and Electronics Engineers Inc., pp. 2696-2700, 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018, Calgary, Canada, 18-04-15. https://doi.org/10.1109/ICASSP.2018.8462680

Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition. / Chen, Sih Huei; Lee, Yuan Shan; Hsu, Yu Sheng; Wu, Chung-Hsien; Wang, Jia Ching.

2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Vol. 2018-April Institute of Electrical and Electronics Engineers Inc., 2018. p. 2696-2700 8462680.

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

TY - GEN

T1 - Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition

AU - Chen, Sih Huei

AU - Lee, Yuan Shan

AU - Hsu, Yu Sheng

AU - Wu, Chung-Hsien

AU - Wang, Jia Ching

PY - 2018/9/10

Y1 - 2018/9/10

N2 - Learning a low-dimensional image representation yields effective and efficient face recognition. The use of such a representation helps to weaken the curse of dimensionality. However, the traditional facial representation method is not robust against partial occlusions or variations of expression. To solve this problem, this paper proposes a more reliable, complex-valued representation of facial image. The robust representation is based on the proposed locality-preserving complex-valued Gaussian process latent variable model (LP-CGPLVM). In the LP-CGPLVM, the Euler formula is utilized to transform original facial images into the complex domain. A proper complex GP is employed to model the mapping between the complex-valued high-dimensional data and the corresponding low-dimensional representation. Moreover, the locality-preserving constraint is taken into consideration to preserve the neighborhood data structure. The experimental results indicate that our proposed method is robust against partial occlusions and various facial expressions.

AB - Learning a low-dimensional image representation yields effective and efficient face recognition. The use of such a representation helps to weaken the curse of dimensionality. However, the traditional facial representation method is not robust against partial occlusions or variations of expression. To solve this problem, this paper proposes a more reliable, complex-valued representation of facial image. The robust representation is based on the proposed locality-preserving complex-valued Gaussian process latent variable model (LP-CGPLVM). In the LP-CGPLVM, the Euler formula is utilized to transform original facial images into the complex domain. A proper complex GP is employed to model the mapping between the complex-valued high-dimensional data and the corresponding low-dimensional representation. Moreover, the locality-preserving constraint is taken into consideration to preserve the neighborhood data structure. The experimental results indicate that our proposed method is robust against partial occlusions and various facial expressions.

UR - http://www.scopus.com/inward/record.url?scp=85054247706&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054247706&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2018.8462680

DO - 10.1109/ICASSP.2018.8462680

M3 - Conference contribution

SN - 9781538646588

VL - 2018-April

SP - 2696

EP - 2700

BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chen SH, Lee YS, Hsu YS, Wu C-H, Wang JC. Locality-preserving complex-valued Gaussian process latent variable model for robust face recognition. In 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Vol. 2018-April. Institute of Electrical and Electronics Engineers Inc. 2018. p. 2696-2700. 8462680 https://doi.org/10.1109/ICASSP.2018.8462680