Masked FER-2013: Augmented Dataset for Facial Expression Recognition

Bin Han; Hanseob Kim; Gerard Jounghyun Kim; Jae In Hwang

doi:10.1109/VRW58643.2023.00216

Masked FER-2013: Augmented Dataset for Facial Expression Recognition

Bin Han
, Hanseob Kim
, Gerard Jounghyun Kim
, Jae In Hwang^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

This poster introduces the Masked FER-2013 dataset that can be used to analyze facial emotions in people wearing masks and train a recognizer. The FER-2013 dataset containing face images annotated with seven emotions was modified by synthesizing mask images into the lower portion of the face. Based on the quantitative evaluation, our dataset can improve the accuracy of CNN, VGG, and ResNet models' emotion recognition in masked images by a maximum of 46%. Additionally, as a use case, we present an application that recognizes the emotions of a masked person, generates emotional face animation, and augments it on a real mask during video conferencing.

Original language	English
Title of host publication	Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	747-748
Number of pages	2
ISBN (Electronic)	9798350348392
DOIs	https://doi.org/10.1109/VRW58643.2023.00216
Publication status	Published - 2023
Event	2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023 - Shanghai, China Duration: 2023 Mar 25 → 2023 Mar 29

Publication series

Name	Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

Conference

Conference	2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
Country/Territory	China
City	Shanghai
Period	23/3/25 → 23/3/29

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Artificial intelligence
Computer vision
Computing methodologies
Human computer interaction (HCI)
Human-centered computing
Interaction paradigms-Mixed / augmented reality
Object recognition

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Science Applications
Human-Computer Interaction
Media Technology

Access to Document

10.1109/VRW58643.2023.00216

Cite this

Han, B., Kim, H., Kim, G. J., & Hwang, J. I. (2023). Masked FER-2013: Augmented Dataset for Facial Expression Recognition. In Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023 (pp. 747-748). (Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VRW58643.2023.00216

Masked FER-2013: Augmented Dataset for Facial Expression Recognition. / Han, Bin; Kim, Hanseob; Kim, Gerard Jounghyun et al.
Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 747-748 (Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Han, B, Kim, H, Kim, GJ & Hwang, JI 2023, Masked FER-2013: Augmented Dataset for Facial Expression Recognition. in Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023. Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023, Institute of Electrical and Electronics Engineers Inc., pp. 747-748, 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023, Shanghai, China, 23/3/25. https://doi.org/10.1109/VRW58643.2023.00216

Han B, Kim H, Kim GJ, Hwang JI. Masked FER-2013: Augmented Dataset for Facial Expression Recognition. In Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 747-748. (Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023). doi: 10.1109/VRW58643.2023.00216

Han, Bin ; Kim, Hanseob ; Kim, Gerard Jounghyun et al. / Masked FER-2013 : Augmented Dataset for Facial Expression Recognition. Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 747-748 (Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023).

@inproceedings{d1199cf304a546db9990b05059e6e4d9,

title = "Masked FER-2013: Augmented Dataset for Facial Expression Recognition",

abstract = "This poster introduces the Masked FER-2013 dataset that can be used to analyze facial emotions in people wearing masks and train a recognizer. The FER-2013 dataset containing face images annotated with seven emotions was modified by synthesizing mask images into the lower portion of the face. Based on the quantitative evaluation, our dataset can improve the accuracy of CNN, VGG, and ResNet models' emotion recognition in masked images by a maximum of 46\%. Additionally, as a use case, we present an application that recognizes the emotions of a masked person, generates emotional face animation, and augments it on a real mask during video conferencing.",

keywords = "Artificial intelligence, Computer vision, Computing methodologies, Human computer interaction (HCI), Human-centered computing, Interaction paradigms-Mixed / augmented reality, Object recognition",

author = "Bin Han and Hanseob Kim and Kim, \{Gerard Jounghyun\} and Hwang, \{Jae In\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023 ; Conference date: 25-03-2023 Through 29-03-2023",

year = "2023",

doi = "10.1109/VRW58643.2023.00216",

language = "English",

series = "Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "747--748",

booktitle = "Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023",

}

TY - GEN

T1 - Masked FER-2013

T2 - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

AU - Han, Bin

AU - Kim, Hanseob

AU - Kim, Gerard Jounghyun

AU - Hwang, Jae In

PY - 2023

Y1 - 2023

N2 - This poster introduces the Masked FER-2013 dataset that can be used to analyze facial emotions in people wearing masks and train a recognizer. The FER-2013 dataset containing face images annotated with seven emotions was modified by synthesizing mask images into the lower portion of the face. Based on the quantitative evaluation, our dataset can improve the accuracy of CNN, VGG, and ResNet models' emotion recognition in masked images by a maximum of 46%. Additionally, as a use case, we present an application that recognizes the emotions of a masked person, generates emotional face animation, and augments it on a real mask during video conferencing.

AB - This poster introduces the Masked FER-2013 dataset that can be used to analyze facial emotions in people wearing masks and train a recognizer. The FER-2013 dataset containing face images annotated with seven emotions was modified by synthesizing mask images into the lower portion of the face. Based on the quantitative evaluation, our dataset can improve the accuracy of CNN, VGG, and ResNet models' emotion recognition in masked images by a maximum of 46%. Additionally, as a use case, we present an application that recognizes the emotions of a masked person, generates emotional face animation, and augments it on a real mask during video conferencing.

KW - Artificial intelligence

KW - Computer vision

KW - Computing methodologies

KW - Human computer interaction (HCI)

KW - Human-centered computing

KW - Interaction paradigms-Mixed / augmented reality

KW - Object recognition

UR - https://www.scopus.com/pages/publications/85159689018

U2 - 10.1109/VRW58643.2023.00216

DO - 10.1109/VRW58643.2023.00216

M3 - Conference contribution

AN - SCOPUS:85159689018

T3 - Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

SP - 747

EP - 748

BT - Proceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 25 March 2023 through 29 March 2023

ER -

Masked FER-2013: Augmented Dataset for Facial Expression Recognition

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this