Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Emotion expression is a type of nonverbal communication (i.e. wordless cues) between people, where affect plays the role of interpersonal communication with information conveyed by facial and/or body expressions. Much can be
understood about how people are feeling through their expressions, which are crucial for everyday communication and interaction. This paper presents a study on spatiotemporal feature extraction based on tracked facial landmarks. The features are tested with multiple classification methods to verify whether they are discriminative enough for an automatic emotion recognition system. The Karolinska Directed Emotional Faces (KDEF) [1] were used to determine features representing the human facial expressions of angry, disgusted, happy, sad, afraid, surprised and neutral. The resulting set of features were tested using K-fold cross-validation. Experimental results show that facial expressions
can be recognised correctly with an accuracy of up to 87% when using the newly-developed features and a multiclass Support Vector Machine classifier.
Original languageEnglish
Title of host publicationProceedings of the 9th International Conference on Intelligent Systems
Number of pages6
ISBN (Electronic)978-1-5386-7097-2
Publication statusPublished - 26 Sep 2018
Event9th international Conference on Intelligent Systems 2018
- Madeira Island, Portugal
Duration: 25 Sep 201827 Sep 2018

Conference

Conference9th international Conference on Intelligent Systems 2018
CountryPortugal
CityMadeira Island
Period25/09/1827/09/18

Fingerprint

Communication
Support vector machines
Feature extraction
Classifiers

Keywords

  • HRI
  • emotion recognition

Cite this

Golzadeh, H., Faria, D., Manso, L. J., Ekárt, A., & Buckingham, C. D. (2018). Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks. In Proceedings of the 9th International Conference on Intelligent Systems
@inproceedings{fb0faed9982543e9a56c74937bf2887f,
title = "Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks",
abstract = "Emotion expression is a type of nonverbal communication (i.e. wordless cues) between people, where affect plays the role of interpersonal communication with information conveyed by facial and/or body expressions. Much can be understood about how people are feeling through their expressions, which are crucial for everyday communication and interaction. This paper presents a study on spatiotemporal feature extraction based on tracked facial landmarks. The features are tested with multiple classification methods to verify whether they are discriminative enough for an automatic emotion recognition system. The Karolinska Directed Emotional Faces (KDEF) [1] were used to determine features representing the human facial expressions of angry, disgusted, happy, sad, afraid, surprised and neutral. The resulting set of features were tested using K-fold cross-validation. Experimental results show that facial expressions can be recognised correctly with an accuracy of up to 87{\%} when using the newly-developed features and a multiclass Support Vector Machine classifier.",
keywords = "HRI, emotion recognition",
author = "Hamid Golzadeh and Diego Faria and Manso, {Luis J.} and Anik{\'o} Ek{\'a}rt and Buckingham, {Christopher D}",
year = "2018",
month = "9",
day = "26",
language = "English",
booktitle = "Proceedings of the 9th International Conference on Intelligent Systems",

}

Golzadeh, H, Faria, D, Manso, LJ, Ekárt, A & Buckingham, CD 2018, Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks. in Proceedings of the 9th International Conference on Intelligent Systems . 9th international Conference on Intelligent Systems 2018
, Madeira Island, Portugal, 25/09/18.

Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks. / Golzadeh, Hamid; Faria, Diego; Manso, Luis J.; Ekárt, Anikó; Buckingham, Christopher D.

Proceedings of the 9th International Conference on Intelligent Systems . 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks

AU - Golzadeh, Hamid

AU - Faria, Diego

AU - Manso, Luis J.

AU - Ekárt, Anikó

AU - Buckingham, Christopher D

PY - 2018/9/26

Y1 - 2018/9/26

N2 - Emotion expression is a type of nonverbal communication (i.e. wordless cues) between people, where affect plays the role of interpersonal communication with information conveyed by facial and/or body expressions. Much can be understood about how people are feeling through their expressions, which are crucial for everyday communication and interaction. This paper presents a study on spatiotemporal feature extraction based on tracked facial landmarks. The features are tested with multiple classification methods to verify whether they are discriminative enough for an automatic emotion recognition system. The Karolinska Directed Emotional Faces (KDEF) [1] were used to determine features representing the human facial expressions of angry, disgusted, happy, sad, afraid, surprised and neutral. The resulting set of features were tested using K-fold cross-validation. Experimental results show that facial expressions can be recognised correctly with an accuracy of up to 87% when using the newly-developed features and a multiclass Support Vector Machine classifier.

AB - Emotion expression is a type of nonverbal communication (i.e. wordless cues) between people, where affect plays the role of interpersonal communication with information conveyed by facial and/or body expressions. Much can be understood about how people are feeling through their expressions, which are crucial for everyday communication and interaction. This paper presents a study on spatiotemporal feature extraction based on tracked facial landmarks. The features are tested with multiple classification methods to verify whether they are discriminative enough for an automatic emotion recognition system. The Karolinska Directed Emotional Faces (KDEF) [1] were used to determine features representing the human facial expressions of angry, disgusted, happy, sad, afraid, surprised and neutral. The resulting set of features were tested using K-fold cross-validation. Experimental results show that facial expressions can be recognised correctly with an accuracy of up to 87% when using the newly-developed features and a multiclass Support Vector Machine classifier.

KW - HRI

KW - emotion recognition

M3 - Conference contribution

BT - Proceedings of the 9th International Conference on Intelligent Systems

ER -

Golzadeh H, Faria D, Manso LJ, Ekárt A, Buckingham CD. Emotion Recognition using Spatiotemporal Features from Facial Expression Landmarks. In Proceedings of the 9th International Conference on Intelligent Systems . 2018