Towards the development of affective facial expression recognition for human-robot interaction

Diego Resende Faria, Mario Vieira, Fernanda C.C. Faria

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

Abstract

Affective facial expression is a key feature of non-verbal behavior and is considered as a symptom of an internal emotional state. Emotion recognition plays an important role in social communication: human-human and also for human-robot interaction. This work aims at the development of a framework able to recognise human emotions through facial expression for human-robot interaction. Simple features based on facial landmarks distances and angles are extracted to feed a dynamic probabilistic classification framework. The public online dataset Karolinska Directed Emotional Faces (KDEF) [12] is used to learn seven different emotions (e.g. Angry, fearful, disgusted, happy, sad, surprised, and neutral) performed by seventy subjects. Offline and on-the-fly tests were carried out: leave-one-out cross validation tests using the dataset and on-the-fly tests during human-robot interactions. Preliminary results show that the proposed framework can correctly recognise human facial expressions with potential to be used in human-robot interaction scenarios.

Original languageEnglish
Title of host publicationACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding)
Place of PublicationNew York, NY (US)
PublisherACM
Pages300-304
Number of pages5
ISBN (Electronic)978-1-4503-5227-7
DOIs
Publication statusPublished - 21 Jun 2017
Event10th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2017 - Island of Rhodes, Greece
Duration: 21 Jun 201723 Jun 2017

Conference

Conference10th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2017
CountryGreece
CityIsland of Rhodes
Period21/06/1723/06/17

Fingerprint

Human robot interaction
Communication

Bibliographical note

-

Keywords

  • affective facial expressions
  • emotion recognition
  • human-robot interaction

Cite this

Faria, D. R., Vieira, M., & Faria, F. C. C. (2017). Towards the development of affective facial expression recognition for human-robot interaction. In ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding) (pp. 300-304). New York, NY (US): ACM. https://doi.org/10.1145/3056540.3076199
Faria, Diego Resende ; Vieira, Mario ; Faria, Fernanda C.C. / Towards the development of affective facial expression recognition for human-robot interaction. ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding). New York, NY (US) : ACM, 2017. pp. 300-304
@inproceedings{b9becda53d3d4dfb95a08fff4c8634d6,
title = "Towards the development of affective facial expression recognition for human-robot interaction",
abstract = "Affective facial expression is a key feature of non-verbal behavior and is considered as a symptom of an internal emotional state. Emotion recognition plays an important role in social communication: human-human and also for human-robot interaction. This work aims at the development of a framework able to recognise human emotions through facial expression for human-robot interaction. Simple features based on facial landmarks distances and angles are extracted to feed a dynamic probabilistic classification framework. The public online dataset Karolinska Directed Emotional Faces (KDEF) [12] is used to learn seven different emotions (e.g. Angry, fearful, disgusted, happy, sad, surprised, and neutral) performed by seventy subjects. Offline and on-the-fly tests were carried out: leave-one-out cross validation tests using the dataset and on-the-fly tests during human-robot interactions. Preliminary results show that the proposed framework can correctly recognise human facial expressions with potential to be used in human-robot interaction scenarios.",
keywords = "affective facial expressions, emotion recognition, human-robot interaction",
author = "Faria, {Diego Resende} and Mario Vieira and Faria, {Fernanda C.C.}",
note = "-",
year = "2017",
month = "6",
day = "21",
doi = "10.1145/3056540.3076199",
language = "English",
pages = "300--304",
booktitle = "ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding)",
publisher = "ACM",
address = "United States",

}

Faria, DR, Vieira, M & Faria, FCC 2017, Towards the development of affective facial expression recognition for human-robot interaction. in ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding). ACM, New York, NY (US), pp. 300-304, 10th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2017, Island of Rhodes, Greece, 21/06/17. https://doi.org/10.1145/3056540.3076199

Towards the development of affective facial expression recognition for human-robot interaction. / Faria, Diego Resende; Vieira, Mario; Faria, Fernanda C.C.

ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding). New York, NY (US) : ACM, 2017. p. 300-304.

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

TY - GEN

T1 - Towards the development of affective facial expression recognition for human-robot interaction

AU - Faria, Diego Resende

AU - Vieira, Mario

AU - Faria, Fernanda C.C.

N1 - -

PY - 2017/6/21

Y1 - 2017/6/21

N2 - Affective facial expression is a key feature of non-verbal behavior and is considered as a symptom of an internal emotional state. Emotion recognition plays an important role in social communication: human-human and also for human-robot interaction. This work aims at the development of a framework able to recognise human emotions through facial expression for human-robot interaction. Simple features based on facial landmarks distances and angles are extracted to feed a dynamic probabilistic classification framework. The public online dataset Karolinska Directed Emotional Faces (KDEF) [12] is used to learn seven different emotions (e.g. Angry, fearful, disgusted, happy, sad, surprised, and neutral) performed by seventy subjects. Offline and on-the-fly tests were carried out: leave-one-out cross validation tests using the dataset and on-the-fly tests during human-robot interactions. Preliminary results show that the proposed framework can correctly recognise human facial expressions with potential to be used in human-robot interaction scenarios.

AB - Affective facial expression is a key feature of non-verbal behavior and is considered as a symptom of an internal emotional state. Emotion recognition plays an important role in social communication: human-human and also for human-robot interaction. This work aims at the development of a framework able to recognise human emotions through facial expression for human-robot interaction. Simple features based on facial landmarks distances and angles are extracted to feed a dynamic probabilistic classification framework. The public online dataset Karolinska Directed Emotional Faces (KDEF) [12] is used to learn seven different emotions (e.g. Angry, fearful, disgusted, happy, sad, surprised, and neutral) performed by seventy subjects. Offline and on-the-fly tests were carried out: leave-one-out cross validation tests using the dataset and on-the-fly tests during human-robot interactions. Preliminary results show that the proposed framework can correctly recognise human facial expressions with potential to be used in human-robot interaction scenarios.

KW - affective facial expressions

KW - emotion recognition

KW - human-robot interaction

UR - http://dl.acm.org/citation.cfm?doid=3056540.3076199

UR - http://www.scopus.com/inward/record.url?scp=85025124790&partnerID=8YFLogxK

U2 - 10.1145/3056540.3076199

DO - 10.1145/3056540.3076199

M3 - Conference contribution

AN - SCOPUS:85025124790

SP - 300

EP - 304

BT - ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding)

PB - ACM

CY - New York, NY (US)

ER -

Faria DR, Vieira M, Faria FCC. Towards the development of affective facial expression recognition for human-robot interaction. In ACM PETRA'17: 10th International Conference on PErvasive Technologies Related to Assistive Environments (NOTION: Human Behaviour Monitoring, Interpretation and Understanding). New York, NY (US): ACM. 2017. p. 300-304 https://doi.org/10.1145/3056540.3076199