Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition

Jianhua Li; Jinxin Wang; Jihong Pei; Yang Zhao

doi:10.1007/978-981-99-7869-4_27

Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition

Jianhua Li, Jinxin Wang^*, Jihong Pei, Yang Zhao

^*Corresponding author for this work

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

Low-resolution face image recognition is a research focus in computer vision and pattern recognition. In this paper, the potential relationship between matched high-resolution face and low-resolution face images is considered to propose the regularized loose coupled deep non-negative basis matrix factorization (RLCDNBMF) architecture, which uses regularized deep non-negative basis matrix factorization for high-resolution images and couples its coefficient matrix with the coefficient matrix obtained from low-resolution non-negative factorization, so that the discriminative information of high-resolution face images can be fully utilized to guide the non-negative matrix factorization of low-resolution face images. Comparative experiments are conducted on three mainstream face databases, and the experimental results show that the method can improve the accuracy of low-resolution face recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

Original language	English
Title of host publication	Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings
Editors	Songmao Zhang, Yonggang Zhang
Publisher	Springer Singapore
Pages	340-353
ISBN (Electronic)	9789819978694
ISBN (Print)	9789819978687
DOIs	https://doi.org/10.1007/978-981-99-7869-4_27
Publication status	Published - 2023
Event	3rd International Conference on Artificial Intelligence Logic and Applications (AILA 2023) - Changchun, China Duration: 5 Aug 2023 → 6 Aug 2023 http://ailasym.com/AILA2023/index.html

Publication series

Name	Communications in Computer and Information Science
Volume	1917
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	3rd International Conference on Artificial Intelligence Logic and Applications (AILA 2023)
Abbreviated title	AILA2023
Place	China
City	Changchun
Period	5/08/23 → 6/08/23
Internet address	http://ailasym.com/AILA2023/index.html

Research Keywords

Coupled mapping
Deep Factorization Architecture
Low-resolution Face Image Recognition
Non-negative Matrix Factorization

Access Output

10.1007/978-981-99-7869-4_27

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Li, J., Wang, J., Pei, J., & Zhao, Y. (2023). Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition. In S. Zhang, & Y. Zhang (Eds.), Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings (pp. 340-353). (Communications in Computer and Information Science; Vol. 1917). Springer Singapore. https://doi.org/10.1007/978-981-99-7869-4_27

Li, Jianhua ; Wang, Jinxin ; Pei, Jihong et al. / Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition. Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings. editor / Songmao Zhang ; Yonggang Zhang. Springer Singapore, 2023. pp. 340-353 (Communications in Computer and Information Science).

@inproceedings{4bda7ef0254d4c2f85d32e47252f0e2e,

title = "Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition",

abstract = "Low-resolution face image recognition is a research focus in computer vision and pattern recognition. In this paper, the potential relationship between matched high-resolution face and low-resolution face images is considered to propose the regularized loose coupled deep non-negative basis matrix factorization (RLCDNBMF) architecture, which uses regularized deep non-negative basis matrix factorization for high-resolution images and couples its coefficient matrix with the coefficient matrix obtained from low-resolution non-negative factorization, so that the discriminative information of high-resolution face images can be fully utilized to guide the non-negative matrix factorization of low-resolution face images. Comparative experiments are conducted on three mainstream face databases, and the experimental results show that the method can improve the accuracy of low-resolution face recognition. {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.",

keywords = "Coupled mapping, Deep Factorization Architecture, Low-resolution Face Image Recognition, Non-negative Matrix Factorization",

author = "Jianhua Li and Jinxin Wang and Jihong Pei and Yang Zhao",

year = "2023",

doi = "10.1007/978-981-99-7869-4_27",

language = "English",

isbn = "9789819978687",

series = "Communications in Computer and Information Science",

publisher = "Springer Singapore",

pages = "340--353",

editor = "Songmao Zhang and Yonggang Zhang",

booktitle = "Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings",

address = "Singapore",

note = "3rd International Conference on Artificial Intelligence Logic and Applications (AILA 2023), AILA2023 ; Conference date: 05-08-2023 Through 06-08-2023",

url = "http://ailasym.com/AILA2023/index.html",

}

Li, J, Wang, J, Pei, J & Zhao, Y 2023, Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition. in S Zhang & Y Zhang (eds), Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings. Communications in Computer and Information Science, vol. 1917, Springer Singapore, pp. 340-353, 3rd International Conference on Artificial Intelligence Logic and Applications (AILA 2023), Changchun, China, 5/08/23. https://doi.org/10.1007/978-981-99-7869-4_27

Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition. / Li, Jianhua; Wang, Jinxin; Pei, Jihong et al.
Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings. ed. / Songmao Zhang; Yonggang Zhang. Springer Singapore, 2023. p. 340-353 (Communications in Computer and Information Science; Vol. 1917).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition

AU - Li, Jianhua

AU - Wang, Jinxin

AU - Pei, Jihong

AU - Zhao, Yang

PY - 2023

Y1 - 2023

N2 - Low-resolution face image recognition is a research focus in computer vision and pattern recognition. In this paper, the potential relationship between matched high-resolution face and low-resolution face images is considered to propose the regularized loose coupled deep non-negative basis matrix factorization (RLCDNBMF) architecture, which uses regularized deep non-negative basis matrix factorization for high-resolution images and couples its coefficient matrix with the coefficient matrix obtained from low-resolution non-negative factorization, so that the discriminative information of high-resolution face images can be fully utilized to guide the non-negative matrix factorization of low-resolution face images. Comparative experiments are conducted on three mainstream face databases, and the experimental results show that the method can improve the accuracy of low-resolution face recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

AB - Low-resolution face image recognition is a research focus in computer vision and pattern recognition. In this paper, the potential relationship between matched high-resolution face and low-resolution face images is considered to propose the regularized loose coupled deep non-negative basis matrix factorization (RLCDNBMF) architecture, which uses regularized deep non-negative basis matrix factorization for high-resolution images and couples its coefficient matrix with the coefficient matrix obtained from low-resolution non-negative factorization, so that the discriminative information of high-resolution face images can be fully utilized to guide the non-negative matrix factorization of low-resolution face images. Comparative experiments are conducted on three mainstream face databases, and the experimental results show that the method can improve the accuracy of low-resolution face recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

KW - Coupled mapping

KW - Deep Factorization Architecture

KW - Low-resolution Face Image Recognition

KW - Non-negative Matrix Factorization

UR - http://www.scopus.com/inward/record.url?scp=85177852377&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85177852377&origin=recordpage

U2 - 10.1007/978-981-99-7869-4_27

DO - 10.1007/978-981-99-7869-4_27

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9789819978687

T3 - Communications in Computer and Information Science

SP - 340

EP - 353

BT - Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings

A2 - Zhang, Songmao

A2 - Zhang, Yonggang

PB - Springer Singapore

T2 - 3rd International Conference on Artificial Intelligence Logic and Applications (AILA 2023)

Y2 - 5 August 2023 through 6 August 2023

ER -

Li J, Wang J, Pei J, Zhao Y. Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition. In Zhang S, Zhang Y, editors, Artificial Intelligence Logic and Applications - The 3rd International Conference, AILA 2023, Proceedings. Springer Singapore. 2023. p. 340-353. (Communications in Computer and Information Science). Epub 2023 Nov 15. doi: 10.1007/978-981-99-7869-4_27

Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this