Facial expression recognition based on feature point vector and texture deformation energy parameters

Ji Zheng Yi, Xia Mao, Ishizuka Mitsuru, Yu Li Xue

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Facial expression recognition is a popular and difficult research field in human-computer interaction. In order to remove effectively the differences in expression feature caused by individual differences, this paper firstly presents the feature point distance ratio coefficient based on feature point vector, and then gives the concept of texture deformation energy parameters. Finally, merges previously mentioned two parts to form a new expression feature for facial expression recognition. The proposed method is tested in the Cohn-Kanade database and the BHU facial expression database, and the experimental results show the recognition rates of the proposed method comparing with the existing ones increased by 4.5% and 3.9%.

Original languageEnglish
Pages (from-to)2403-2410
Number of pages8
JournalDianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology
Volume35
Issue number10
DOIs
Publication statusPublished - 2013 Oct
Externally publishedYes

Fingerprint

Textures
Human computer interaction

Keywords

  • Facial expression recognition
  • Feature point vector
  • Radial basis function neural network
  • Texture deformation energy parameters

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Facial expression recognition based on feature point vector and texture deformation energy parameters. / Yi, Ji Zheng; Mao, Xia; Mitsuru, Ishizuka; Xue, Yu Li.

In: Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, Vol. 35, No. 10, 10.2013, p. 2403-2410.

Research output: Contribution to journalArticle

@article{696d677585bd4473adff5a8e36077016,
title = "Facial expression recognition based on feature point vector and texture deformation energy parameters",
abstract = "Facial expression recognition is a popular and difficult research field in human-computer interaction. In order to remove effectively the differences in expression feature caused by individual differences, this paper firstly presents the feature point distance ratio coefficient based on feature point vector, and then gives the concept of texture deformation energy parameters. Finally, merges previously mentioned two parts to form a new expression feature for facial expression recognition. The proposed method is tested in the Cohn-Kanade database and the BHU facial expression database, and the experimental results show the recognition rates of the proposed method comparing with the existing ones increased by 4.5{\%} and 3.9{\%}.",
keywords = "Facial expression recognition, Feature point vector, Radial basis function neural network, Texture deformation energy parameters",
author = "Yi, {Ji Zheng} and Xia Mao and Ishizuka Mitsuru and Xue, {Yu Li}",
year = "2013",
month = "10",
doi = "10.3724/SP.J.1146.2012.01569",
language = "English",
volume = "35",
pages = "2403--2410",
journal = "Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology",
issn = "1009-5896",
publisher = "Science Press",
number = "10",

}

TY - JOUR

T1 - Facial expression recognition based on feature point vector and texture deformation energy parameters

AU - Yi, Ji Zheng

AU - Mao, Xia

AU - Mitsuru, Ishizuka

AU - Xue, Yu Li

PY - 2013/10

Y1 - 2013/10

N2 - Facial expression recognition is a popular and difficult research field in human-computer interaction. In order to remove effectively the differences in expression feature caused by individual differences, this paper firstly presents the feature point distance ratio coefficient based on feature point vector, and then gives the concept of texture deformation energy parameters. Finally, merges previously mentioned two parts to form a new expression feature for facial expression recognition. The proposed method is tested in the Cohn-Kanade database and the BHU facial expression database, and the experimental results show the recognition rates of the proposed method comparing with the existing ones increased by 4.5% and 3.9%.

AB - Facial expression recognition is a popular and difficult research field in human-computer interaction. In order to remove effectively the differences in expression feature caused by individual differences, this paper firstly presents the feature point distance ratio coefficient based on feature point vector, and then gives the concept of texture deformation energy parameters. Finally, merges previously mentioned two parts to form a new expression feature for facial expression recognition. The proposed method is tested in the Cohn-Kanade database and the BHU facial expression database, and the experimental results show the recognition rates of the proposed method comparing with the existing ones increased by 4.5% and 3.9%.

KW - Facial expression recognition

KW - Feature point vector

KW - Radial basis function neural network

KW - Texture deformation energy parameters

UR - http://www.scopus.com/inward/record.url?scp=84885452274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885452274&partnerID=8YFLogxK

U2 - 10.3724/SP.J.1146.2012.01569

DO - 10.3724/SP.J.1146.2012.01569

M3 - Article

AN - SCOPUS:84885452274

VL - 35

SP - 2403

EP - 2410

JO - Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology

JF - Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology

SN - 1009-5896

IS - 10

ER -