Facial expression recognition based on fusion of gabor and LBP features

Quan You Zhao; Bao Chang Pan; Jian Jia Pan; Yuan Yan Tang

doi:10.1109/ICWAPR.2008.4635805

Facial expression recognition based on fusion of gabor and LBP features

Quan You Zhao
, Bao Chang Pan
, Jian Jia Pan
, Yuan Yan Tang

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

30 Citations (Scopus)

Abstract

A new person-independent facial expression recognition algorithm based on fusion of Gabor and LBP Features with OLPP is presented. Aiming at the deficiency of common Gabor feature extraction method, a new Gabor feature extraction method is proposed. Each Gabor wavelet representation of an image is divided into small subblocks, then the mean value and standard deviation in each subblock are calculated, and the statistics of all Gabor wavelet representations are connected as the feature vector. Taking into account the outstanding performance of LBP to extract local texture, we combine local statistic features of Gabor wavelets with the LBP features as feature vector. After using OLPP to reduce the feature dimension of fusion features, the facial expression image is classified by nearest neighbor method. Experimental results on two databases indicate the proposed method has higher recognition rate compared with single feature method and other methods.

Original language	English
Title of host publication	Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR
Publisher	IEEE
Pages	362-367
Number of pages	6
Volume	1
ISBN (Electronic)	9781424422395
ISBN (Print)	9781424422388
DOIs	https://doi.org/10.1109/ICWAPR.2008.4635805
Publication status	Published - 30 Aug 2008
Event	2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2008 - Hong Kong, China Duration: 30 Aug 2008 → 31 Aug 2008

Publication series

Name	Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR
Publisher	IEEE
ISSN (Print)	2158-5695
ISSN (Electronic)	2158-5709

Conference

Conference	2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2008
Country/Territory	China
City	Hong Kong
Period	30/08/08 → 31/08/08

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

Facial expression recognition
Gabor wavelet
LBP
OLPP

Access to Document

10.1109/ICWAPR.2008.4635805

Cite this

Zhao, Q. Y., Pan, B. C., Pan, J. J., & Tang, Y. Y. (2008). Facial expression recognition based on fusion of gabor and LBP features. In Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR (Vol. 1, pp. 362-367). (Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR). IEEE. https://doi.org/10.1109/ICWAPR.2008.4635805

@inproceedings{ebbb29133a0c46f6ac8d1d7be132c9df,

title = "Facial expression recognition based on fusion of gabor and LBP features",

abstract = "A new person-independent facial expression recognition algorithm based on fusion of Gabor and LBP Features with OLPP is presented. Aiming at the deficiency of common Gabor feature extraction method, a new Gabor feature extraction method is proposed. Each Gabor wavelet representation of an image is divided into small subblocks, then the mean value and standard deviation in each subblock are calculated, and the statistics of all Gabor wavelet representations are connected as the feature vector. Taking into account the outstanding performance of LBP to extract local texture, we combine local statistic features of Gabor wavelets with the LBP features as feature vector. After using OLPP to reduce the feature dimension of fusion features, the facial expression image is classified by nearest neighbor method. Experimental results on two databases indicate the proposed method has higher recognition rate compared with single feature method and other methods.",

keywords = "Facial expression recognition, Gabor wavelet, LBP, OLPP",

author = "Zhao, \{Quan You\} and Pan, \{Bao Chang\} and Pan, \{Jian Jia\} and Tang, \{Yuan Yan\}",

note = "Publisher copyright: {\textcopyright} 2008 IEEE; 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2008 ; Conference date: 30-08-2008 Through 31-08-2008",

year = "2008",

month = aug,

day = "30",

doi = "10.1109/ICWAPR.2008.4635805",

language = "English",

isbn = "9781424422388",

volume = "1",

series = "Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR",

publisher = "IEEE",

pages = "362--367",

booktitle = "Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR",

address = "United States",

}

Zhao, QY, Pan, BC, Pan, JJ & Tang, YY 2008, Facial expression recognition based on fusion of gabor and LBP features. in Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR. vol. 1, Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR, IEEE, pp. 362-367, 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2008, Hong Kong, China, 30/08/08. https://doi.org/10.1109/ICWAPR.2008.4635805

Facial expression recognition based on fusion of gabor and LBP features. / Zhao, Quan You; Pan, Bao Chang; Pan, Jian Jia et al.
Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR. Vol. 1 IEEE, 2008. p. 362-367 (Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Facial expression recognition based on fusion of gabor and LBP features

AU - Zhao, Quan You

AU - Pan, Bao Chang

AU - Pan, Jian Jia

AU - Tang, Yuan Yan

PY - 2008/8/30

Y1 - 2008/8/30

N2 - A new person-independent facial expression recognition algorithm based on fusion of Gabor and LBP Features with OLPP is presented. Aiming at the deficiency of common Gabor feature extraction method, a new Gabor feature extraction method is proposed. Each Gabor wavelet representation of an image is divided into small subblocks, then the mean value and standard deviation in each subblock are calculated, and the statistics of all Gabor wavelet representations are connected as the feature vector. Taking into account the outstanding performance of LBP to extract local texture, we combine local statistic features of Gabor wavelets with the LBP features as feature vector. After using OLPP to reduce the feature dimension of fusion features, the facial expression image is classified by nearest neighbor method. Experimental results on two databases indicate the proposed method has higher recognition rate compared with single feature method and other methods.

AB - A new person-independent facial expression recognition algorithm based on fusion of Gabor and LBP Features with OLPP is presented. Aiming at the deficiency of common Gabor feature extraction method, a new Gabor feature extraction method is proposed. Each Gabor wavelet representation of an image is divided into small subblocks, then the mean value and standard deviation in each subblock are calculated, and the statistics of all Gabor wavelet representations are connected as the feature vector. Taking into account the outstanding performance of LBP to extract local texture, we combine local statistic features of Gabor wavelets with the LBP features as feature vector. After using OLPP to reduce the feature dimension of fusion features, the facial expression image is classified by nearest neighbor method. Experimental results on two databases indicate the proposed method has higher recognition rate compared with single feature method and other methods.

KW - Facial expression recognition

KW - Gabor wavelet

KW - LBP

KW - OLPP

UR - https://www.scopus.com/pages/publications/56749184902

U2 - 10.1109/ICWAPR.2008.4635805

DO - 10.1109/ICWAPR.2008.4635805

M3 - Conference proceeding

AN - SCOPUS:56749184902

SN - 9781424422388

VL - 1

T3 - Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR

SP - 362

EP - 367

BT - Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR

PB - IEEE

T2 - 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2008

Y2 - 30 August 2008 through 31 August 2008

ER -

Zhao QY, Pan BC, Pan JJ, Tang YY. Facial expression recognition based on fusion of gabor and LBP features. In Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR. Vol. 1. IEEE. 2008. p. 362-367. (Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR). doi: 10.1109/ICWAPR.2008.4635805

Facial expression recognition based on fusion of gabor and LBP features

Abstract

Publication series

Conference

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this