Extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions

Rosdiyana Samad, Hideyuki Sawada

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Facial expression recognition has recently become an important research area, and many efforts have been made in facial feature extraction and its classification to improve face recognition systems. Most researchers adopt a posed facial expression database in their experiments, but in a real-life situation the facial expressions may not be very obvious. This article describes the extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions. The objective of our research was to investigate the performance of a facial expression recognition system with a minimum number of features of the Gabor wavelet. In this research, principal component analysis (PCA) is employed to compress the Gabor features. We also discuss the selection of the minimum number of Gabor features that will perform the best in a recognition task employing a multiclass support vector machine (SVM) classifier. The performance of facial expression recognition using our approach is compared with those obtained previously by other researchers using other approaches. Experimental results showed that our proposed technique is successful in recognizing natural facial expressions by using a small number of Gabor features with an 81.7% recognition rate. In addition, we identify the relationship between the human vision and computer vision in recognizing natural facial expressions.

Original languageEnglish
Pages (from-to)21-31
Number of pages11
JournalArtificial Life and Robotics
Volume16
Issue number1
DOIs
Publication statusPublished - 2011 Jun
Externally publishedYes

Fingerprint

Facial Expression
Face recognition
Principal component analysis
Computer vision
Support vector machines
Feature extraction
Classifiers
Research
Research Personnel
Principal Component Analysis
Experiments
Databases

Keywords

  • Facial expression
  • Gabor wavelet
  • Multiclass SVM
  • Principal component analysis (PCA)

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence

Cite this

Extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions. / Samad, Rosdiyana; Sawada, Hideyuki.

In: Artificial Life and Robotics, Vol. 16, No. 1, 06.2011, p. 21-31.

Research output: Contribution to journalArticle

@article{c5bb2d81ca784522b231734788cf4c3d,
title = "Extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions",
abstract = "Facial expression recognition has recently become an important research area, and many efforts have been made in facial feature extraction and its classification to improve face recognition systems. Most researchers adopt a posed facial expression database in their experiments, but in a real-life situation the facial expressions may not be very obvious. This article describes the extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions. The objective of our research was to investigate the performance of a facial expression recognition system with a minimum number of features of the Gabor wavelet. In this research, principal component analysis (PCA) is employed to compress the Gabor features. We also discuss the selection of the minimum number of Gabor features that will perform the best in a recognition task employing a multiclass support vector machine (SVM) classifier. The performance of facial expression recognition using our approach is compared with those obtained previously by other researchers using other approaches. Experimental results showed that our proposed technique is successful in recognizing natural facial expressions by using a small number of Gabor features with an 81.7{\%} recognition rate. In addition, we identify the relationship between the human vision and computer vision in recognizing natural facial expressions.",
keywords = "Facial expression, Gabor wavelet, Multiclass SVM, Principal component analysis (PCA)",
author = "Rosdiyana Samad and Hideyuki Sawada",
year = "2011",
month = "6",
doi = "10.1007/s10015-011-0871-6",
language = "English",
volume = "16",
pages = "21--31",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "1",

}

TY - JOUR

T1 - Extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions

AU - Samad, Rosdiyana

AU - Sawada, Hideyuki

PY - 2011/6

Y1 - 2011/6

N2 - Facial expression recognition has recently become an important research area, and many efforts have been made in facial feature extraction and its classification to improve face recognition systems. Most researchers adopt a posed facial expression database in their experiments, but in a real-life situation the facial expressions may not be very obvious. This article describes the extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions. The objective of our research was to investigate the performance of a facial expression recognition system with a minimum number of features of the Gabor wavelet. In this research, principal component analysis (PCA) is employed to compress the Gabor features. We also discuss the selection of the minimum number of Gabor features that will perform the best in a recognition task employing a multiclass support vector machine (SVM) classifier. The performance of facial expression recognition using our approach is compared with those obtained previously by other researchers using other approaches. Experimental results showed that our proposed technique is successful in recognizing natural facial expressions by using a small number of Gabor features with an 81.7% recognition rate. In addition, we identify the relationship between the human vision and computer vision in recognizing natural facial expressions.

AB - Facial expression recognition has recently become an important research area, and many efforts have been made in facial feature extraction and its classification to improve face recognition systems. Most researchers adopt a posed facial expression database in their experiments, but in a real-life situation the facial expressions may not be very obvious. This article describes the extraction of the minimum number of Gabor wavelet parameters for the recognition of natural facial expressions. The objective of our research was to investigate the performance of a facial expression recognition system with a minimum number of features of the Gabor wavelet. In this research, principal component analysis (PCA) is employed to compress the Gabor features. We also discuss the selection of the minimum number of Gabor features that will perform the best in a recognition task employing a multiclass support vector machine (SVM) classifier. The performance of facial expression recognition using our approach is compared with those obtained previously by other researchers using other approaches. Experimental results showed that our proposed technique is successful in recognizing natural facial expressions by using a small number of Gabor features with an 81.7% recognition rate. In addition, we identify the relationship between the human vision and computer vision in recognizing natural facial expressions.

KW - Facial expression

KW - Gabor wavelet

KW - Multiclass SVM

KW - Principal component analysis (PCA)

UR - http://www.scopus.com/inward/record.url?scp=79959665425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959665425&partnerID=8YFLogxK

U2 - 10.1007/s10015-011-0871-6

DO - 10.1007/s10015-011-0871-6

M3 - Article

AN - SCOPUS:79959665425

VL - 16

SP - 21

EP - 31

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 1

ER -