Maximum volume constrained graph nonnegative matrix factorization for facial expression recognition

Viet Hang Duong; Manh Quan Bui; Jian Jiun Ding; Bach Tung Pham; Pham The Bao; Jia Ching Wang

doi:10.1587/transfun.E100.A.3081

Maximum volume constrained graph nonnegative matrix factorization for facial expression recognition

Viet Hang Duong, Manh Quan Bui, Jian Jiun Ding, Bach Tung Pham, Pham The Bao, Jia Ching Wang

Research output: Contribution to journal › Article › peer-review

Abstract

In this work, two new proposed NMF models are developed for facial expression recognition. They are called maximum volume constrained nonnegative matrix factorization (MV-NMF) and maximum volume constrained graph nonnegative matrix factorization (MV-GNMF). They achieve sparseness from a larger simplicial cone constraint and the extracted features preserve the topological structure of the original images.

Original language	English
Pages (from-to)	3081-3085
Number of pages	5
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E100A
Issue number	12
DOIs	https://doi.org/10.1587/transfun.E100.A.3081
State	Published - Dec 2017

Keywords

Facial expression recognition
Feature extraction
Graph regularized
Nonnegative matrix factorization
Projected gradient descent

Access to Document

10.1587/transfun.E100.A.3081

Cite this

@article{aa124053dc504c318864f30192c83397,

title = "Maximum volume constrained graph nonnegative matrix factorization for facial expression recognition",

abstract = "In this work, two new proposed NMF models are developed for facial expression recognition. They are called maximum volume constrained nonnegative matrix factorization (MV-NMF) and maximum volume constrained graph nonnegative matrix factorization (MV-GNMF). They achieve sparseness from a larger simplicial cone constraint and the extracted features preserve the topological structure of the original images.",

keywords = "Facial expression recognition, Feature extraction, Graph regularized, Nonnegative matrix factorization, Projected gradient descent",

author = "Duong, {Viet Hang} and Bui, {Manh Quan} and Ding, {Jian Jiun} and Pham, {Bach Tung} and Bao, {Pham The} and Wang, {Jia Ching}",

note = "Publisher Copyright: Copyright {\textcopyright} 2017 The Institute of Electronics, Information and Communication Engineers.",

year = "2017",

month = dec,

doi = "10.1587/transfun.E100.A.3081",

language = "???core.languages.en_GB???",

volume = "E100A",

pages = "3081--3085",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

number = "12",

}

TY - JOUR

T1 - Maximum volume constrained graph nonnegative matrix factorization for facial expression recognition

AU - Duong, Viet Hang

AU - Bui, Manh Quan

AU - Ding, Jian Jiun

AU - Pham, Bach Tung

AU - Bao, Pham The

AU - Wang, Jia Ching

PY - 2017/12

Y1 - 2017/12

N2 - In this work, two new proposed NMF models are developed for facial expression recognition. They are called maximum volume constrained nonnegative matrix factorization (MV-NMF) and maximum volume constrained graph nonnegative matrix factorization (MV-GNMF). They achieve sparseness from a larger simplicial cone constraint and the extracted features preserve the topological structure of the original images.

AB - In this work, two new proposed NMF models are developed for facial expression recognition. They are called maximum volume constrained nonnegative matrix factorization (MV-NMF) and maximum volume constrained graph nonnegative matrix factorization (MV-GNMF). They achieve sparseness from a larger simplicial cone constraint and the extracted features preserve the topological structure of the original images.

KW - Facial expression recognition

KW - Feature extraction

KW - Graph regularized

KW - Nonnegative matrix factorization

KW - Projected gradient descent

UR - http://www.scopus.com/inward/record.url?scp=85038211828&partnerID=8YFLogxK

U2 - 10.1587/transfun.E100.A.3081

DO - 10.1587/transfun.E100.A.3081

M3 - 期刊論文

AN - SCOPUS:85038211828

SN - 0916-8508

VL - E100A

SP - 3081

EP - 3085

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 12

ER -

Maximum volume constrained graph nonnegative matrix factorization for facial expression recognition

Abstract

Keywords

Access to Document

Fingerprint

Cite this