Person-independent expression recognition based on person-similarity weighted expression feature

Huachun Tan; Yujin Zhang; Hao Chen; Yanan Zhao; Wuhong Wang

doi:10.3969/j.issn.1004-4132.2010.01.019

Person-independent expression recognition based on person-similarity weighted expression feature

Huachun Tan^*, Yujin Zhang, Hao Chen, Yanan Zhao, Wuhong Wang

^*Corresponding author for this work

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

7 Citations (Scopus)

Abstract

A new method to extract person-independent expression feature based on higher-order singular value decomposition (HOSVD) is proposed for facial expression recognition. Based on the assumption that similar persons have similar facial expression appearance and shape, the person-similarity weighted expression feature is proposed to estimate the expression feature of test persons. As a result, the estimated expression feature can reduce the influence of individuals caused by insufficient training data, and hence become less person-dependent. The proposed method is tested on Cohn-Kanade facial expression database and Japanese female facial expression (JAFFE) database. Person-independent experimental results show the superiority of the proposed method over the existing methods.

Original language	English
Pages (from-to)	118-126
Number of pages	9
Journal	Journal of Systems Engineering and Electronics
Volume	21
Issue number	1
DOIs	https://doi.org/10.3969/j.issn.1004-4132.2010.01.019
Publication status	Published - 26 Feb 2010

Keywords

Facial expression recognition
Feature estimation
Higher-order singular value decomposition
Person-independent expression feature

Access to Document

10.3969/j.issn.1004-4132.2010.01.019

Cite this

@article{30f8493014834cc89733e7cc8185f9d0,

title = "Person-independent expression recognition based on person-similarity weighted expression feature",

abstract = "A new method to extract person-independent expression feature based on higher-order singular value decomposition (HOSVD) is proposed for facial expression recognition. Based on the assumption that similar persons have similar facial expression appearance and shape, the person-similarity weighted expression feature is proposed to estimate the expression feature of test persons. As a result, the estimated expression feature can reduce the influence of individuals caused by insufficient training data, and hence become less person-dependent. The proposed method is tested on Cohn-Kanade facial expression database and Japanese female facial expression (JAFFE) database. Person-independent experimental results show the superiority of the proposed method over the existing methods.",

keywords = "Facial expression recognition, Feature estimation, Higher-order singular value decomposition, Person-independent expression feature",

author = "Huachun Tan and Yujin Zhang and Hao Chen and Yanan Zhao and Wuhong Wang",

year = "2010",

month = feb,

day = "26",

doi = "10.3969/j.issn.1004-4132.2010.01.019",

language = "English",

volume = "21",

pages = "118--126",

journal = "Journal of Systems Engineering and Electronics",

issn = "1671-1793",

publisher = "Kexue Chubaneshe/Science Press",

number = "1",

}

TY - JOUR

T1 - Person-independent expression recognition based on person-similarity weighted expression feature

AU - Tan, Huachun

AU - Zhang, Yujin

AU - Chen, Hao

AU - Zhao, Yanan

AU - Wang, Wuhong

PY - 2010/2/26

Y1 - 2010/2/26

N2 - A new method to extract person-independent expression feature based on higher-order singular value decomposition (HOSVD) is proposed for facial expression recognition. Based on the assumption that similar persons have similar facial expression appearance and shape, the person-similarity weighted expression feature is proposed to estimate the expression feature of test persons. As a result, the estimated expression feature can reduce the influence of individuals caused by insufficient training data, and hence become less person-dependent. The proposed method is tested on Cohn-Kanade facial expression database and Japanese female facial expression (JAFFE) database. Person-independent experimental results show the superiority of the proposed method over the existing methods.

AB - A new method to extract person-independent expression feature based on higher-order singular value decomposition (HOSVD) is proposed for facial expression recognition. Based on the assumption that similar persons have similar facial expression appearance and shape, the person-similarity weighted expression feature is proposed to estimate the expression feature of test persons. As a result, the estimated expression feature can reduce the influence of individuals caused by insufficient training data, and hence become less person-dependent. The proposed method is tested on Cohn-Kanade facial expression database and Japanese female facial expression (JAFFE) database. Person-independent experimental results show the superiority of the proposed method over the existing methods.

KW - Facial expression recognition

KW - Feature estimation

KW - Higher-order singular value decomposition

KW - Person-independent expression feature

UR - http://www.scopus.com/inward/record.url?scp=77956269192&partnerID=8YFLogxK

U2 - 10.3969/j.issn.1004-4132.2010.01.019

DO - 10.3969/j.issn.1004-4132.2010.01.019

M3 - Article

AN - SCOPUS:77956269192

SN - 1671-1793

VL - 21

SP - 118

EP - 126

JO - Journal of Systems Engineering and Electronics

JF - Journal of Systems Engineering and Electronics

IS - 1

ER -

Person-independent expression recognition based on person-similarity weighted expression feature

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this