A new constrained nonnegative matrix factorization for facial expression recognition

Viet Hang Duong; Manh Quan Bui; Pham The Bao; Jia Ching Wang

doi:10.1109/ICOT.2017.8336093

A new constrained nonnegative matrix factorization for facial expression recognition

Viet Hang Duong
, Manh Quan Bui
, Pham The Bao
, Jia Ching Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

A new NMF model, spatial constrained graph sparse nonnegative matrix factorization (SGSNMF) is adopted for facial expression recognition. In this model, the extracted features preserve the topological structure of the original images and achieve sparseness from L₂ constraint on coefficient matrix, meanwhile the base satisfy pixel dispersion penalty. The proposed method takes advantage of the project gradient decent and is based on the alternating nonnegative least square framework. Experiments on two facial expression recognition scenarios that involve a whole face and an occluded face reveal that the proposed algorithm outperforms the prevalent NMF methods.

Original language	English
Title of host publication	Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017
Editors	Minghui Dong, Lei Wang, Yanfeng Lu, Haizhou Li
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	79-82
Number of pages	4
ISBN (Electronic)	9781538632758
DOIs	https://doi.org/10.1109/ICOT.2017.8336093
State	Published - 2 Jul 2017
Event	5th International Conference on Orange Technologies, ICOT 2017 - Singapore, Singapore Duration: 8 Dec 2017 → 10 Dec 2017

Publication series

Name	Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017
Volume	2018-January

Conference

Conference	5th International Conference on Orange Technologies, ICOT 2017
Country/Territory	Singapore
City	Singapore
Period	8/12/17 → 10/12/17

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Facial expression recognition
Graph regularization
Nonnegative matrix factorization
Projectedgradient descent

Access to Document

10.1109/ICOT.2017.8336093

Cite this

Duong, V. H., Bui, M. Q., Bao, P. T., & Wang, J. C. (2017). A new constrained nonnegative matrix factorization for facial expression recognition. In M. Dong, L. Wang, Y. Lu, & H. Li (Eds.), Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017 (pp. 79-82). (Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOT.2017.8336093

Duong, Viet Hang ; Bui, Manh Quan ; Bao, Pham The et al. / A new constrained nonnegative matrix factorization for facial expression recognition. Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017. editor / Minghui Dong ; Lei Wang ; Yanfeng Lu ; Haizhou Li. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 79-82 (Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017).

@inproceedings{9f96352b2f7f4e29875da39be1f12c3b,

title = "A new constrained nonnegative matrix factorization for facial expression recognition",

abstract = "A new NMF model, spatial constrained graph sparse nonnegative matrix factorization (SGSNMF) is adopted for facial expression recognition. In this model, the extracted features preserve the topological structure of the original images and achieve sparseness from L2 constraint on coefficient matrix, meanwhile the base satisfy pixel dispersion penalty. The proposed method takes advantage of the project gradient decent and is based on the alternating nonnegative least square framework. Experiments on two facial expression recognition scenarios that involve a whole face and an occluded face reveal that the proposed algorithm outperforms the prevalent NMF methods.",

keywords = "Facial expression recognition, Graph regularization, Nonnegative matrix factorization, Projectedgradient descent",

author = "Duong, \{Viet Hang\} and Bui, \{Manh Quan\} and Bao, \{Pham The\} and Wang, \{Jia Ching\}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 5th International Conference on Orange Technologies, ICOT 2017 ; Conference date: 08-12-2017 Through 10-12-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICOT.2017.8336093",

language = "???core.languages.en\_GB???",

series = "Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "79--82",

editor = "Minghui Dong and Lei Wang and Yanfeng Lu and Haizhou Li",

booktitle = "Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017",

}

Duong, VH, Bui, MQ, Bao, PT & Wang, JC 2017, A new constrained nonnegative matrix factorization for facial expression recognition. in M Dong, L Wang, Y Lu & H Li (eds), Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017. Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 79-82, 5th International Conference on Orange Technologies, ICOT 2017, Singapore, Singapore, 8/12/17. https://doi.org/10.1109/ICOT.2017.8336093

A new constrained nonnegative matrix factorization for facial expression recognition. / Duong, Viet Hang; Bui, Manh Quan; Bao, Pham The et al.
Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017. ed. / Minghui Dong; Lei Wang; Yanfeng Lu; Haizhou Li. Institute of Electrical and Electronics Engineers Inc., 2017. p. 79-82 (Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017; Vol. 2018-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new constrained nonnegative matrix factorization for facial expression recognition

AU - Duong, Viet Hang

AU - Bui, Manh Quan

AU - Bao, Pham The

AU - Wang, Jia Ching

PY - 2017/7/2

Y1 - 2017/7/2

N2 - A new NMF model, spatial constrained graph sparse nonnegative matrix factorization (SGSNMF) is adopted for facial expression recognition. In this model, the extracted features preserve the topological structure of the original images and achieve sparseness from L2 constraint on coefficient matrix, meanwhile the base satisfy pixel dispersion penalty. The proposed method takes advantage of the project gradient decent and is based on the alternating nonnegative least square framework. Experiments on two facial expression recognition scenarios that involve a whole face and an occluded face reveal that the proposed algorithm outperforms the prevalent NMF methods.

AB - A new NMF model, spatial constrained graph sparse nonnegative matrix factorization (SGSNMF) is adopted for facial expression recognition. In this model, the extracted features preserve the topological structure of the original images and achieve sparseness from L2 constraint on coefficient matrix, meanwhile the base satisfy pixel dispersion penalty. The proposed method takes advantage of the project gradient decent and is based on the alternating nonnegative least square framework. Experiments on two facial expression recognition scenarios that involve a whole face and an occluded face reveal that the proposed algorithm outperforms the prevalent NMF methods.

KW - Facial expression recognition

KW - Graph regularization

KW - Nonnegative matrix factorization

KW - Projectedgradient descent

UR - https://www.scopus.com/pages/publications/85048558545

U2 - 10.1109/ICOT.2017.8336093

DO - 10.1109/ICOT.2017.8336093

M3 - 會議論文篇章

AN - SCOPUS:85048558545

T3 - Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017

SP - 79

EP - 82

BT - Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017

A2 - Dong, Minghui

A2 - Wang, Lei

A2 - Lu, Yanfeng

A2 - Li, Haizhou

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Orange Technologies, ICOT 2017

Y2 - 8 December 2017 through 10 December 2017

ER -

Duong VH, Bui MQ, Bao PT, Wang JC. A new constrained nonnegative matrix factorization for facial expression recognition. In Dong M, Wang L, Lu Y, Li H, editors, Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 79-82. (Proceedings of the 2017 International Conference on Orange Technologies, ICOT 2017). doi: 10.1109/ICOT.2017.8336093

A new constrained nonnegative matrix factorization for facial expression recognition

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this