On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition

Andrés Espinel; Noel Pérez; Daniel Riofrío; Diego S. Benítez; Ricardo Flores Moyano

doi:10.1007/978-3-030-91308-3_2

On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition

Andrés Espinel, Noel Pérez, Daniel Riofrío, Diego S. Benítez, Ricardo Flores Moyano

Universidad San Francisco de Quito

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

1 Scopus citations

Abstract

This work compares face gesture recognition methods based on deep learning convolutional neural network and autoencoder architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing databases. We validated the proposed architectures on four different databases: Jaffe, CK+, FACES, and the combination of them over a five-fold cross-validation strategy. The DCNN4 was the best model in the Jaffe and FACES databases, obtaining accuracy scores of 95 % and 97 %, respectively. The DCNN2 achieved the best accuracy performance of 94 % in the CK+ database. Finally, the DCNN+Autoencoder stands as the best model in the combination of all databases (Jaffe & CK+ & FACES), achieving an accuracy score of 92 %. Moreover, according to the cross-entropy loss function, the best model per database did not incur overfitting.

Original language	English
Title of host publication	Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers
Editors	Alvaro David Orjuela-Cañón, Jesus A. Lopez, Julián David Arias-Londoño, Juan Carlos Figueroa-García
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	18-30
Number of pages	13
ISBN (Print)	9783030913076
DOIs	https://doi.org/10.1007/978-3-030-91308-3_2
State	Published - 2022
Event	4th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Virtual, Online Duration: 27 May 2021 → 28 May 2021

Publication series

Name	Communications in Computer and Information Science
Volume	1471 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	4th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021
City	Virtual, Online
Period	27/05/21 → 28/05/21

Keywords

Artificial intelligence
Deep-learning models
Face emotion recognition
Face gesture classification
Face images

Access to Document

10.1007/978-3-030-91308-3_2

Cite this

Espinel, A., Pérez, N., Riofrío, D., Benítez, D. S., & Moyano, R. F. (2022). On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition. In A. D. Orjuela-Cañón, J. A. Lopez, J. D. Arias-Londoño, & J. C. Figueroa-García (Eds.), Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers (pp. 18-30). (Communications in Computer and Information Science; Vol. 1471 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-91308-3_2

Espinel, Andrés ; Pérez, Noel ; Riofrío, Daniel et al. / On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition. Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers. editor / Alvaro David Orjuela-Cañón ; Jesus A. Lopez ; Julián David Arias-Londoño ; Juan Carlos Figueroa-García. Springer Science and Business Media Deutschland GmbH, 2022. pp. 18-30 (Communications in Computer and Information Science).

@inproceedings{8663abd962764b48865789b590b1ed9e,

title = "On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition",

abstract = "This work compares face gesture recognition methods based on deep learning convolutional neural network and autoencoder architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing databases. We validated the proposed architectures on four different databases: Jaffe, CK+, FACES, and the combination of them over a five-fold cross-validation strategy. The DCNN4 was the best model in the Jaffe and FACES databases, obtaining accuracy scores of 95 % and 97 %, respectively. The DCNN2 achieved the best accuracy performance of 94 % in the CK+ database. Finally, the DCNN+Autoencoder stands as the best model in the combination of all databases (Jaffe & CK+ & FACES), achieving an accuracy score of 92 %. Moreover, according to the cross-entropy loss function, the best model per database did not incur overfitting.",

keywords = "Artificial intelligence, Deep-learning models, Face emotion recognition, Face gesture classification, Face images",

author = "Andr{\'e}s Espinel and Noel P{\'e}rez and Daniel Riofr{\'i}o and Ben{\'i}tez, {Diego S.} and Moyano, {Ricardo Flores}",

note = "Publisher Copyright: {\textcopyright} 2022, Springer Nature Switzerland AG.; 4th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 ; Conference date: 27-05-2021 Through 28-05-2021",

year = "2022",

doi = "10.1007/978-3-030-91308-3_2",

language = "Ingl{\'e}s",

isbn = "9783030913076",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "18--30",

editor = "Orjuela-Ca{\~n}{\'o}n, {Alvaro David} and Lopez, {Jesus A.} and Arias-Londo{\~n}o, {Juli{\'a}n David} and Figueroa-Garc{\'i}a, {Juan Carlos}",

booktitle = "Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers",

}

Espinel, A, Pérez, N , Riofrío, D , Benítez, DS & Moyano, RF 2022, On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition. in AD Orjuela-Cañón, JA Lopez, JD Arias-Londoño & JC Figueroa-García (eds), Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers. Communications in Computer and Information Science, vol. 1471 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 18-30, 4th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021, Virtual, Online, 27/05/21. https://doi.org/10.1007/978-3-030-91308-3_2

On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition. / Espinel, Andrés; Pérez, Noel ; Riofrío, Daniel et al.
Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers. ed. / Alvaro David Orjuela-Cañón; Jesus A. Lopez; Julián David Arias-Londoño; Juan Carlos Figueroa-García. Springer Science and Business Media Deutschland GmbH, 2022. p. 18-30 (Communications in Computer and Information Science; Vol. 1471 CCIS).

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

TY - GEN

T1 - On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition

AU - Espinel, Andrés

AU - Pérez, Noel

AU - Riofrío, Daniel

AU - Benítez, Diego S.

AU - Moyano, Ricardo Flores

PY - 2022

Y1 - 2022

N2 - This work compares face gesture recognition methods based on deep learning convolutional neural network and autoencoder architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing databases. We validated the proposed architectures on four different databases: Jaffe, CK+, FACES, and the combination of them over a five-fold cross-validation strategy. The DCNN4 was the best model in the Jaffe and FACES databases, obtaining accuracy scores of 95 % and 97 %, respectively. The DCNN2 achieved the best accuracy performance of 94 % in the CK+ database. Finally, the DCNN+Autoencoder stands as the best model in the combination of all databases (Jaffe & CK+ & FACES), achieving an accuracy score of 92 %. Moreover, according to the cross-entropy loss function, the best model per database did not incur overfitting.

AB - This work compares face gesture recognition methods based on deep learning convolutional neural network and autoencoder architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing databases. We validated the proposed architectures on four different databases: Jaffe, CK+, FACES, and the combination of them over a five-fold cross-validation strategy. The DCNN4 was the best model in the Jaffe and FACES databases, obtaining accuracy scores of 95 % and 97 %, respectively. The DCNN2 achieved the best accuracy performance of 94 % in the CK+ database. Finally, the DCNN+Autoencoder stands as the best model in the combination of all databases (Jaffe & CK+ & FACES), achieving an accuracy score of 92 %. Moreover, according to the cross-entropy loss function, the best model per database did not incur overfitting.

KW - Artificial intelligence

KW - Deep-learning models

KW - Face emotion recognition

KW - Face gesture classification

KW - Face images

UR - http://www.scopus.com/inward/record.url?scp=85126259555&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-91308-3_2

DO - 10.1007/978-3-030-91308-3_2

M3 - Contribución a la conferencia

AN - SCOPUS:85126259555

SN - 9783030913076

T3 - Communications in Computer and Information Science

SP - 18

EP - 30

BT - Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers

A2 - Orjuela-Cañón, Alvaro David

A2 - Lopez, Jesus A.

A2 - Arias-Londoño, Julián David

A2 - Figueroa-García, Juan Carlos

PB - Springer Science and Business Media Deutschland GmbH

T2 - 4th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021

Y2 - 27 May 2021 through 28 May 2021

ER -

Espinel A, Pérez N , Riofrío D , Benítez DS , Moyano RF. On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition. In Orjuela-Cañón AD, Lopez JA, Arias-Londoño JD, Figueroa-García JC, editors, Applications of Computational Intelligence - 4th IEEE Colombian Conference, ColCACI 2021, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2022. p. 18-30. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-91308-3_2

On the Use of Convolutional Neural Network Architectures for Facial Emotion Recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this