A training model for fuzzy classification system

Amir Jamshidnezhad, Md. Jan Nordin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In recent years, Fuzzy Logic is considerably used as an intelligent technique to solve the ambiguous problems which are in the human life. Classification of emotions is one of the challenging problems deals with natural conditions of human face, linguistic and paralanguage. As the understanding of emotions, is highly depended on the facial expressions, in this paper a feature based hybrid system is proposed to classify the facial expressions to the basic emotions. The core of expression recognition system is a Mamdani-type fuzzy rule based system to model mathematically the natural conditions. Also, with the purpose of making better performance of fuzzy rule based system, Genetic learning Processes designed for parameter optimization to improve the accuracy and robustness of the system under adverse conditions. To evaluate the system performance, images from Cohn-Kanade database were used and the accuracy rate of 92% was obtained.

Original languageEnglish
Pages (from-to)1127-1132
Number of pages6
JournalAustralian Journal of Basic and Applied Sciences
Volume5
Issue number7
Publication statusPublished - Jul 2011

Fingerprint

Knowledge based systems
Fuzzy rules
Hybrid systems
Linguistics
Fuzzy logic

Keywords

  • Classifier
  • Facial expression recognition
  • Fuzzy system
  • Genetic algorithm
  • Pattern recognition

ASJC Scopus subject areas

  • General

Cite this

A training model for fuzzy classification system. / Jamshidnezhad, Amir; Nordin, Md. Jan.

In: Australian Journal of Basic and Applied Sciences, Vol. 5, No. 7, 07.2011, p. 1127-1132.

Research output: Contribution to journalArticle

@article{614848529d5442bab0e37e67e1129f36,
title = "A training model for fuzzy classification system",
abstract = "In recent years, Fuzzy Logic is considerably used as an intelligent technique to solve the ambiguous problems which are in the human life. Classification of emotions is one of the challenging problems deals with natural conditions of human face, linguistic and paralanguage. As the understanding of emotions, is highly depended on the facial expressions, in this paper a feature based hybrid system is proposed to classify the facial expressions to the basic emotions. The core of expression recognition system is a Mamdani-type fuzzy rule based system to model mathematically the natural conditions. Also, with the purpose of making better performance of fuzzy rule based system, Genetic learning Processes designed for parameter optimization to improve the accuracy and robustness of the system under adverse conditions. To evaluate the system performance, images from Cohn-Kanade database were used and the accuracy rate of 92{\%} was obtained.",
keywords = "Classifier, Facial expression recognition, Fuzzy system, Genetic algorithm, Pattern recognition",
author = "Amir Jamshidnezhad and Nordin, {Md. Jan}",
year = "2011",
month = "7",
language = "English",
volume = "5",
pages = "1127--1132",
journal = "Australian Journal of Basic and Applied Sciences",
issn = "1991-8178",
publisher = "INSInet Publications",
number = "7",

}

TY - JOUR

T1 - A training model for fuzzy classification system

AU - Jamshidnezhad, Amir

AU - Nordin, Md. Jan

PY - 2011/7

Y1 - 2011/7

N2 - In recent years, Fuzzy Logic is considerably used as an intelligent technique to solve the ambiguous problems which are in the human life. Classification of emotions is one of the challenging problems deals with natural conditions of human face, linguistic and paralanguage. As the understanding of emotions, is highly depended on the facial expressions, in this paper a feature based hybrid system is proposed to classify the facial expressions to the basic emotions. The core of expression recognition system is a Mamdani-type fuzzy rule based system to model mathematically the natural conditions. Also, with the purpose of making better performance of fuzzy rule based system, Genetic learning Processes designed for parameter optimization to improve the accuracy and robustness of the system under adverse conditions. To evaluate the system performance, images from Cohn-Kanade database were used and the accuracy rate of 92% was obtained.

AB - In recent years, Fuzzy Logic is considerably used as an intelligent technique to solve the ambiguous problems which are in the human life. Classification of emotions is one of the challenging problems deals with natural conditions of human face, linguistic and paralanguage. As the understanding of emotions, is highly depended on the facial expressions, in this paper a feature based hybrid system is proposed to classify the facial expressions to the basic emotions. The core of expression recognition system is a Mamdani-type fuzzy rule based system to model mathematically the natural conditions. Also, with the purpose of making better performance of fuzzy rule based system, Genetic learning Processes designed for parameter optimization to improve the accuracy and robustness of the system under adverse conditions. To evaluate the system performance, images from Cohn-Kanade database were used and the accuracy rate of 92% was obtained.

KW - Classifier

KW - Facial expression recognition

KW - Fuzzy system

KW - Genetic algorithm

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=82655175319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82655175319&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 1127

EP - 1132

JO - Australian Journal of Basic and Applied Sciences

JF - Australian Journal of Basic and Applied Sciences

SN - 1991-8178

IS - 7

ER -