Facial expression recognition based upon human cognitive regions

Huiquan Zhang, Sha Luo, Osamu Yoshie

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The discovery of associations between local facial features and image features is one of the current challenges in regard to facial expression recognition. To mitigate the negative effects caused by individual differences, this paper proposes an approach based upon human cognition which can recognize facial expression from six human cognitive regions. The proposed approach exploits descriptions of Local Binary Pattern (LBP) to extract the holistic facial area and establishes a pseudo 3D face model for segmenting the human face into six cognitive regions. Finally, we synthesize change trends and volume distribution of LBP of the six regions to recognize the expressions. Unlike many previous studies, this approach recognizes the expressions from regional features instead of holistic facial features. Further, the regional features are more robust than interesting point-based features because of idiosyncrasy of individuals. To validate our proposed approach, we conducted experiments on the Extended CohnKanade (CK+) facial expression database. The results demonstrate that the proposed approach can effectively segment face into specific areas and recognize facial expressions.

Original languageEnglish
Pages (from-to)1148-1156
Number of pages9
JournalIEEJ Transactions on Electronics, Information and Systems
Volume134
Issue number8
DOIs
Publication statusPublished - 2014

Fingerprint

Experiments

Keywords

  • Facial expression recognition
  • Local Binary Pattern
  • Local facial feature
  • Pseudo 3D face model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Facial expression recognition based upon human cognitive regions. / Zhang, Huiquan; Luo, Sha; Yoshie, Osamu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 134, No. 8, 2014, p. 1148-1156.

Research output: Contribution to journalArticle

@article{dfb630c4e75043bc80d86236241c1e6b,
title = "Facial expression recognition based upon human cognitive regions",
abstract = "The discovery of associations between local facial features and image features is one of the current challenges in regard to facial expression recognition. To mitigate the negative effects caused by individual differences, this paper proposes an approach based upon human cognition which can recognize facial expression from six human cognitive regions. The proposed approach exploits descriptions of Local Binary Pattern (LBP) to extract the holistic facial area and establishes a pseudo 3D face model for segmenting the human face into six cognitive regions. Finally, we synthesize change trends and volume distribution of LBP of the six regions to recognize the expressions. Unlike many previous studies, this approach recognizes the expressions from regional features instead of holistic facial features. Further, the regional features are more robust than interesting point-based features because of idiosyncrasy of individuals. To validate our proposed approach, we conducted experiments on the Extended CohnKanade (CK+) facial expression database. The results demonstrate that the proposed approach can effectively segment face into specific areas and recognize facial expressions.",
keywords = "Facial expression recognition, Local Binary Pattern, Local facial feature, Pseudo 3D face model",
author = "Huiquan Zhang and Sha Luo and Osamu Yoshie",
year = "2014",
doi = "10.1541/ieejeiss.134.1148",
language = "English",
volume = "134",
pages = "1148--1156",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "8",

}

TY - JOUR

T1 - Facial expression recognition based upon human cognitive regions

AU - Zhang, Huiquan

AU - Luo, Sha

AU - Yoshie, Osamu

PY - 2014

Y1 - 2014

N2 - The discovery of associations between local facial features and image features is one of the current challenges in regard to facial expression recognition. To mitigate the negative effects caused by individual differences, this paper proposes an approach based upon human cognition which can recognize facial expression from six human cognitive regions. The proposed approach exploits descriptions of Local Binary Pattern (LBP) to extract the holistic facial area and establishes a pseudo 3D face model for segmenting the human face into six cognitive regions. Finally, we synthesize change trends and volume distribution of LBP of the six regions to recognize the expressions. Unlike many previous studies, this approach recognizes the expressions from regional features instead of holistic facial features. Further, the regional features are more robust than interesting point-based features because of idiosyncrasy of individuals. To validate our proposed approach, we conducted experiments on the Extended CohnKanade (CK+) facial expression database. The results demonstrate that the proposed approach can effectively segment face into specific areas and recognize facial expressions.

AB - The discovery of associations between local facial features and image features is one of the current challenges in regard to facial expression recognition. To mitigate the negative effects caused by individual differences, this paper proposes an approach based upon human cognition which can recognize facial expression from six human cognitive regions. The proposed approach exploits descriptions of Local Binary Pattern (LBP) to extract the holistic facial area and establishes a pseudo 3D face model for segmenting the human face into six cognitive regions. Finally, we synthesize change trends and volume distribution of LBP of the six regions to recognize the expressions. Unlike many previous studies, this approach recognizes the expressions from regional features instead of holistic facial features. Further, the regional features are more robust than interesting point-based features because of idiosyncrasy of individuals. To validate our proposed approach, we conducted experiments on the Extended CohnKanade (CK+) facial expression database. The results demonstrate that the proposed approach can effectively segment face into specific areas and recognize facial expressions.

KW - Facial expression recognition

KW - Local Binary Pattern

KW - Local facial feature

KW - Pseudo 3D face model

UR - http://www.scopus.com/inward/record.url?scp=84906555778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906555778&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.134.1148

DO - 10.1541/ieejeiss.134.1148

M3 - Article

VL - 134

SP - 1148

EP - 1156

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 8

ER -