High-level fuzzy linguistic features of facial components in human emotion recognition

Research output: Contribution to journalArticle

Abstract

Emotion is an important element in an interaction since it conveys human perception and response of an event. Unlike verbal words that can be manipulated, emotion is brief, spontaneous and provides more honest information. There are several classes of basic primary human emotions that differ from one another. These classes are happy, sad, fearful, surprised, disgusted, and angry. Meanwhile, a psychologist has developed a set of rules to recognize emotions based on facial expressions. This research aims to develop an artificial intelligent model based on psychological knowledge to recognize emotions by analyzing facial expressions. Moreover, the proposed model has defined high-level fuzzy linguistic features of facial components which distinguish it from existing methods that commonly use lowlevel image features (e.g. color, intensity, histogram, texture). High-level linguistic features (e.g. opened eyes, wrinkled nose) are better at representing human minds than low-level features which are only understood by machines. The model functions by detecting facial points first to locate important facial components; then extracting geometric facial components features which are then applied to a fuzzy facial components inference system resulting in high-level linguistic facial features. In the last step, the high-level linguistic features are applied to a fuzzy emotion inference system which classifies the input image into its respective emotion class based on psychological rules. Experiments conducted using facial expression dataset gave a high accuracy rate of 98.26% for fuzzy facial components linguistic identification. The proposed model also outperformed other classifiers (Fuzzy C-Means, Fuzzy Inference System, and Support Vector Machine). This intelligent model can contribute in various fields, including psychology, health, and education, especially in helping people with emotional disorders (e.g. Alexithymia, Asperger syndrome, and Autism) to recognize emotions.

Original languageEnglish
Pages (from-to)103-129
Number of pages27
JournalJournal of Information and Communication Technology
Volume19
Issue number1
Publication statusPublished - 1 Jan 2020

Fingerprint

Emotion Recognition
Linguistics
Fuzzy inference
Facial Expression
Support vector machines
Identification (control systems)
Classifiers
Textures
Education
Emotion
Human
Health
Color
Human Perception
Fuzzy C-means
Fuzzy Inference System
Model
Histogram
Disorder
Texture

Keywords

  • Basic emotion
  • Emotion recognition
  • Facial components
  • Facial expression
  • Fuzzy system
  • High-level linguistic features

Cite this

@article{69badf5348ae4d398e8193482dbda3eb,
title = "High-level fuzzy linguistic features of facial components in human emotion recognition",
abstract = "Emotion is an important element in an interaction since it conveys human perception and response of an event. Unlike verbal words that can be manipulated, emotion is brief, spontaneous and provides more honest information. There are several classes of basic primary human emotions that differ from one another. These classes are happy, sad, fearful, surprised, disgusted, and angry. Meanwhile, a psychologist has developed a set of rules to recognize emotions based on facial expressions. This research aims to develop an artificial intelligent model based on psychological knowledge to recognize emotions by analyzing facial expressions. Moreover, the proposed model has defined high-level fuzzy linguistic features of facial components which distinguish it from existing methods that commonly use lowlevel image features (e.g. color, intensity, histogram, texture). High-level linguistic features (e.g. opened eyes, wrinkled nose) are better at representing human minds than low-level features which are only understood by machines. The model functions by detecting facial points first to locate important facial components; then extracting geometric facial components features which are then applied to a fuzzy facial components inference system resulting in high-level linguistic facial features. In the last step, the high-level linguistic features are applied to a fuzzy emotion inference system which classifies the input image into its respective emotion class based on psychological rules. Experiments conducted using facial expression dataset gave a high accuracy rate of 98.26{\%} for fuzzy facial components linguistic identification. The proposed model also outperformed other classifiers (Fuzzy C-Means, Fuzzy Inference System, and Support Vector Machine). This intelligent model can contribute in various fields, including psychology, health, and education, especially in helping people with emotional disorders (e.g. Alexithymia, Asperger syndrome, and Autism) to recognize emotions.",
keywords = "Basic emotion, Emotion recognition, Facial components, Facial expression, Fuzzy system, High-level linguistic features",
author = "Liliana, {Dewi Yanti} and Tarzan Basaruddin and Widyanto, {Muhammad Rahmat} and Oriza, {Imelda Ika Dian}",
year = "2020",
month = "1",
day = "1",
language = "English",
volume = "19",
pages = "103--129",
journal = "Journal of Information and Communication Technology",
issn = "1675-414X",
publisher = "Universiti Utara Malaysia Press",
number = "1",

}

TY - JOUR

T1 - High-level fuzzy linguistic features of facial components in human emotion recognition

AU - Liliana, Dewi Yanti

AU - Basaruddin, Tarzan

AU - Widyanto, Muhammad Rahmat

AU - Oriza, Imelda Ika Dian

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Emotion is an important element in an interaction since it conveys human perception and response of an event. Unlike verbal words that can be manipulated, emotion is brief, spontaneous and provides more honest information. There are several classes of basic primary human emotions that differ from one another. These classes are happy, sad, fearful, surprised, disgusted, and angry. Meanwhile, a psychologist has developed a set of rules to recognize emotions based on facial expressions. This research aims to develop an artificial intelligent model based on psychological knowledge to recognize emotions by analyzing facial expressions. Moreover, the proposed model has defined high-level fuzzy linguistic features of facial components which distinguish it from existing methods that commonly use lowlevel image features (e.g. color, intensity, histogram, texture). High-level linguistic features (e.g. opened eyes, wrinkled nose) are better at representing human minds than low-level features which are only understood by machines. The model functions by detecting facial points first to locate important facial components; then extracting geometric facial components features which are then applied to a fuzzy facial components inference system resulting in high-level linguistic facial features. In the last step, the high-level linguistic features are applied to a fuzzy emotion inference system which classifies the input image into its respective emotion class based on psychological rules. Experiments conducted using facial expression dataset gave a high accuracy rate of 98.26% for fuzzy facial components linguistic identification. The proposed model also outperformed other classifiers (Fuzzy C-Means, Fuzzy Inference System, and Support Vector Machine). This intelligent model can contribute in various fields, including psychology, health, and education, especially in helping people with emotional disorders (e.g. Alexithymia, Asperger syndrome, and Autism) to recognize emotions.

AB - Emotion is an important element in an interaction since it conveys human perception and response of an event. Unlike verbal words that can be manipulated, emotion is brief, spontaneous and provides more honest information. There are several classes of basic primary human emotions that differ from one another. These classes are happy, sad, fearful, surprised, disgusted, and angry. Meanwhile, a psychologist has developed a set of rules to recognize emotions based on facial expressions. This research aims to develop an artificial intelligent model based on psychological knowledge to recognize emotions by analyzing facial expressions. Moreover, the proposed model has defined high-level fuzzy linguistic features of facial components which distinguish it from existing methods that commonly use lowlevel image features (e.g. color, intensity, histogram, texture). High-level linguistic features (e.g. opened eyes, wrinkled nose) are better at representing human minds than low-level features which are only understood by machines. The model functions by detecting facial points first to locate important facial components; then extracting geometric facial components features which are then applied to a fuzzy facial components inference system resulting in high-level linguistic facial features. In the last step, the high-level linguistic features are applied to a fuzzy emotion inference system which classifies the input image into its respective emotion class based on psychological rules. Experiments conducted using facial expression dataset gave a high accuracy rate of 98.26% for fuzzy facial components linguistic identification. The proposed model also outperformed other classifiers (Fuzzy C-Means, Fuzzy Inference System, and Support Vector Machine). This intelligent model can contribute in various fields, including psychology, health, and education, especially in helping people with emotional disorders (e.g. Alexithymia, Asperger syndrome, and Autism) to recognize emotions.

KW - Basic emotion

KW - Emotion recognition

KW - Facial components

KW - Facial expression

KW - Fuzzy system

KW - High-level linguistic features

UR - http://www.scopus.com/inward/record.url?scp=85077471982&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85077471982

VL - 19

SP - 103

EP - 129

JO - Journal of Information and Communication Technology

JF - Journal of Information and Communication Technology

SN - 1675-414X

IS - 1

ER -