Emotion recognition using facial expressions in children using the NAO robot

Alejandro Lopez-Rincon

doi:10.1109/CONIELECOMP.2019.8673111

Emotion recognition using facial expressions in children using the NAO robot

Alejandro Lopez-Rincon^*

^*Corresponding author for this work

extern

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

The detection of human emotions from facial expressions is crucial for social interaction. Therefore, several systems of behavioral computing in robotics try to recognize human emotion from images and video, but most of them are trained to classify emotions in adults only. Using the standard of 6 basic emotions: Sadness, happiness, surprise, anger, disgust, and fear, we try to classify the facial expressions using the NAO robot in children. In this study, we make the comparison between the AFFDEX SDK, and a Convolution Neural Network (CNN) with Viola-Jones trained with the AffectNet dataset, and tuned with the NIMH-ChEF dataset using transfer learning to classify facial expressions in children. Then, we test our system comparing the CNN and the AFFDEX SDK for classification in the Child Affective Facial Expression (CAFE) dataset. Finally, we compare both systems using the NAO robot in a subset of the AM-FED and EmoReact datasets.

Original language	English
Title of host publication	CONIELECOMP 2019 - 2019 International Conference on Electronics, Communications and Computers
Publisher	IEEE
Pages	146-153
Number of pages	8
ISBN (Electronic)	9781728111452
DOIs	https://doi.org/10.1109/CONIELECOMP.2019.8673111
Publication status	Published - 22 Mar 2019
Externally published	Yes
Event	2019 International Conference on Electronics, Communications and Computers, CONIELECOMP 2019 - Cholula, Mexico Duration: 27 Feb 2019 → 1 Mar 2019

Conference

Conference	2019 International Conference on Electronics, Communications and Computers, CONIELECOMP 2019
Country/Territory	Mexico
City	Cholula
Period	27/02/19 → 1/03/19

Funding

This work is part of a project1 (#15198) that is included in the research program Technology for Oncology, which is financed by the Netherlands Organization for Scientific Research (NWO), the Dutch Cancer Society (KWF), the TKI Life Sciences & Health, Asolutions, Brocacef, Cancer Health Coach, and Focal Meditech. The research consortium consists of the Centrum Wiskunde & Informatica, Delft University of Technology, the Academic Medical Center, and the Princess Maxima Center.

Keywords

CNN
emotion recognition
human robot interaction

Access to Document

10.1109/CONIELECOMP.2019.8673111

Cite this

@inproceedings{34be0baa12db4502a11200ab5ddd2188,

title = "Emotion recognition using facial expressions in children using the NAO robot",

abstract = "The detection of human emotions from facial expressions is crucial for social interaction. Therefore, several systems of behavioral computing in robotics try to recognize human emotion from images and video, but most of them are trained to classify emotions in adults only. Using the standard of 6 basic emotions: Sadness, happiness, surprise, anger, disgust, and fear, we try to classify the facial expressions using the NAO robot in children. In this study, we make the comparison between the AFFDEX SDK, and a Convolution Neural Network (CNN) with Viola-Jones trained with the AffectNet dataset, and tuned with the NIMH-ChEF dataset using transfer learning to classify facial expressions in children. Then, we test our system comparing the CNN and the AFFDEX SDK for classification in the Child Affective Facial Expression (CAFE) dataset. Finally, we compare both systems using the NAO robot in a subset of the AM-FED and EmoReact datasets.",

keywords = "CNN, emotion recognition, human robot interaction",

author = "Alejandro Lopez-Rincon",

year = "2019",

month = mar,

day = "22",

doi = "10.1109/CONIELECOMP.2019.8673111",

language = "English",

pages = "146--153",

booktitle = "CONIELECOMP 2019 - 2019 International Conference on Electronics, Communications and Computers",

publisher = "IEEE",

address = "United States",

note = "2019 International Conference on Electronics, Communications and Computers, CONIELECOMP 2019 ; Conference date: 27-02-2019 Through 01-03-2019",

}

Lopez-Rincon, A 2019, Emotion recognition using facial expressions in children using the NAO robot. in CONIELECOMP 2019 - 2019 International Conference on Electronics, Communications and Computers., 8673111, IEEE, pp. 146-153, 2019 International Conference on Electronics, Communications and Computers, CONIELECOMP 2019, Cholula, Mexico, 27/02/19. https://doi.org/10.1109/CONIELECOMP.2019.8673111

TY - GEN

T1 - Emotion recognition using facial expressions in children using the NAO robot

AU - Lopez-Rincon, Alejandro

PY - 2019/3/22

Y1 - 2019/3/22

N2 - The detection of human emotions from facial expressions is crucial for social interaction. Therefore, several systems of behavioral computing in robotics try to recognize human emotion from images and video, but most of them are trained to classify emotions in adults only. Using the standard of 6 basic emotions: Sadness, happiness, surprise, anger, disgust, and fear, we try to classify the facial expressions using the NAO robot in children. In this study, we make the comparison between the AFFDEX SDK, and a Convolution Neural Network (CNN) with Viola-Jones trained with the AffectNet dataset, and tuned with the NIMH-ChEF dataset using transfer learning to classify facial expressions in children. Then, we test our system comparing the CNN and the AFFDEX SDK for classification in the Child Affective Facial Expression (CAFE) dataset. Finally, we compare both systems using the NAO robot in a subset of the AM-FED and EmoReact datasets.

AB - The detection of human emotions from facial expressions is crucial for social interaction. Therefore, several systems of behavioral computing in robotics try to recognize human emotion from images and video, but most of them are trained to classify emotions in adults only. Using the standard of 6 basic emotions: Sadness, happiness, surprise, anger, disgust, and fear, we try to classify the facial expressions using the NAO robot in children. In this study, we make the comparison between the AFFDEX SDK, and a Convolution Neural Network (CNN) with Viola-Jones trained with the AffectNet dataset, and tuned with the NIMH-ChEF dataset using transfer learning to classify facial expressions in children. Then, we test our system comparing the CNN and the AFFDEX SDK for classification in the Child Affective Facial Expression (CAFE) dataset. Finally, we compare both systems using the NAO robot in a subset of the AM-FED and EmoReact datasets.

KW - CNN

KW - emotion recognition

KW - human robot interaction

UR - http://www.scopus.com/inward/record.url?scp=85064191934&partnerID=8YFLogxK

U2 - 10.1109/CONIELECOMP.2019.8673111

DO - 10.1109/CONIELECOMP.2019.8673111

M3 - Conference contribution

AN - SCOPUS:85064191934

SP - 146

EP - 153

BT - CONIELECOMP 2019 - 2019 International Conference on Electronics, Communications and Computers

PB - IEEE

T2 - 2019 International Conference on Electronics, Communications and Computers, CONIELECOMP 2019

Y2 - 27 February 2019 through 1 March 2019

ER -

Emotion recognition using facial expressions in children using the NAO robot

Abstract

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this