A facial expression recognition algorithm with supervised orthogonal locality preserving projection

Bin Song, Doo Kwon Baik

Research output: Contribution to journalArticle

Abstract

According to the characteristics of facial expression, this paper presents a facial expression recognition algorithm with supervised orthogonal locality preserving projection (SOLPP) based on combination of Gabor and local binary pattern (LBP) features. Because of the deficiency of traditional Gabor feature extraction method, an innovative feature extraction method based on Gabor local statistic information is proposed. Each Gabor wavelet representation of an image is divided into some sub-blocks. Then the mean value and standard deviation in each sub-block are calculated, and the statistics of all Gabor wavelet representations are connected as feature vector. Taking into account the effectiveness of LBP to extract local expression texture, we combine local statistic features of Gabor wavelets with LBP textural features as composite facial expression features. After utilizing SOLPP to reduce the feature dimension of composite features, the facial expression image is classified by nearest neighbor method. Experimental results on JAFFE database, CED-WYU (1.0) database and TFEID database indicate the proposed method has higher recognition rate compared with other methods.

Original languageEnglish
Pages (from-to)8495-8504
Number of pages10
JournalJournal of Computational and Theoretical Nanoscience
Volume13
Issue number11
DOIs
Publication statusPublished - 2016

Fingerprint

Facial Expression Recognition
Recognition Algorithm
Locality
preserving
projection
Statistics
Projection
Gabor Wavelet
Feature extraction
Facial Expression
statistics
pattern recognition
Composite materials
Binary
Feature Extraction
Statistic
Textures
Composite
composite materials
Nearest Neighbor Method

Keywords

  • Facial expression recognition
  • Gabor
  • Local binary pattern
  • Supervised orthogonal locality preserving projection

ASJC Scopus subject areas

  • Chemistry(all)
  • Materials Science(all)
  • Condensed Matter Physics
  • Computational Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{6d7b8aeaedf5493cb2f78530320c0c58,
title = "A facial expression recognition algorithm with supervised orthogonal locality preserving projection",
abstract = "According to the characteristics of facial expression, this paper presents a facial expression recognition algorithm with supervised orthogonal locality preserving projection (SOLPP) based on combination of Gabor and local binary pattern (LBP) features. Because of the deficiency of traditional Gabor feature extraction method, an innovative feature extraction method based on Gabor local statistic information is proposed. Each Gabor wavelet representation of an image is divided into some sub-blocks. Then the mean value and standard deviation in each sub-block are calculated, and the statistics of all Gabor wavelet representations are connected as feature vector. Taking into account the effectiveness of LBP to extract local expression texture, we combine local statistic features of Gabor wavelets with LBP textural features as composite facial expression features. After utilizing SOLPP to reduce the feature dimension of composite features, the facial expression image is classified by nearest neighbor method. Experimental results on JAFFE database, CED-WYU (1.0) database and TFEID database indicate the proposed method has higher recognition rate compared with other methods.",
keywords = "Facial expression recognition, Gabor, Local binary pattern, Supervised orthogonal locality preserving projection",
author = "Bin Song and Baik, {Doo Kwon}",
year = "2016",
doi = "10.1166/jctn.2016.6003",
language = "English",
volume = "13",
pages = "8495--8504",
journal = "Journal of Computational and Theoretical Nanoscience",
issn = "1546-1955",
publisher = "American Scientific Publishers",
number = "11",

}

TY - JOUR

T1 - A facial expression recognition algorithm with supervised orthogonal locality preserving projection

AU - Song, Bin

AU - Baik, Doo Kwon

PY - 2016

Y1 - 2016

N2 - According to the characteristics of facial expression, this paper presents a facial expression recognition algorithm with supervised orthogonal locality preserving projection (SOLPP) based on combination of Gabor and local binary pattern (LBP) features. Because of the deficiency of traditional Gabor feature extraction method, an innovative feature extraction method based on Gabor local statistic information is proposed. Each Gabor wavelet representation of an image is divided into some sub-blocks. Then the mean value and standard deviation in each sub-block are calculated, and the statistics of all Gabor wavelet representations are connected as feature vector. Taking into account the effectiveness of LBP to extract local expression texture, we combine local statistic features of Gabor wavelets with LBP textural features as composite facial expression features. After utilizing SOLPP to reduce the feature dimension of composite features, the facial expression image is classified by nearest neighbor method. Experimental results on JAFFE database, CED-WYU (1.0) database and TFEID database indicate the proposed method has higher recognition rate compared with other methods.

AB - According to the characteristics of facial expression, this paper presents a facial expression recognition algorithm with supervised orthogonal locality preserving projection (SOLPP) based on combination of Gabor and local binary pattern (LBP) features. Because of the deficiency of traditional Gabor feature extraction method, an innovative feature extraction method based on Gabor local statistic information is proposed. Each Gabor wavelet representation of an image is divided into some sub-blocks. Then the mean value and standard deviation in each sub-block are calculated, and the statistics of all Gabor wavelet representations are connected as feature vector. Taking into account the effectiveness of LBP to extract local expression texture, we combine local statistic features of Gabor wavelets with LBP textural features as composite facial expression features. After utilizing SOLPP to reduce the feature dimension of composite features, the facial expression image is classified by nearest neighbor method. Experimental results on JAFFE database, CED-WYU (1.0) database and TFEID database indicate the proposed method has higher recognition rate compared with other methods.

KW - Facial expression recognition

KW - Gabor

KW - Local binary pattern

KW - Supervised orthogonal locality preserving projection

UR - http://www.scopus.com/inward/record.url?scp=85015163633&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015163633&partnerID=8YFLogxK

U2 - 10.1166/jctn.2016.6003

DO - 10.1166/jctn.2016.6003

M3 - Article

AN - SCOPUS:85015163633

VL - 13

SP - 8495

EP - 8504

JO - Journal of Computational and Theoretical Nanoscience

JF - Journal of Computational and Theoretical Nanoscience

SN - 1546-1955

IS - 11

ER -