Face Gesture Recognition Using Deep-Learning Models

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

doi:10.1109/ColCACI52978.2021.9469528

Face Gesture Recognition Using Deep-Learning Models

Universidad San Francisco de Quito

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

7 Scopus citations

Abstract

This work compares face gesture recognition methods based on deep learning convolutional neural network (DCNN) architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing datasets. We validated the proposed architectures on three different databases: Jaffe, CK+, and the combination of both databases (Jaffe CK+) over a five-fold cross-validation strategy. The DCNN4, DCNN2, and DCNN+Autoencoder models achieved best performance mean accuracy scores of 95%, 94%, and 96% for the Jaffe, CK+, and Jaffe CK+ databases, respectively. Moreover, according to the cross-entropy loss function, the selected models did not incur overfitting.

Original language	English
Title of host publication	2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings
Editors	Alvaro David Orjuela-Canon
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665435345
DOIs	https://doi.org/10.1109/ColCACI52978.2021.9469528
State	Published - 26 May 2021
Event	2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Virtual, Online, Colombia Duration: 26 May 2021 → 28 May 2021

Publication series

Name	2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings

Conference

Conference	2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021
Country/Territory	Colombia
City	Virtual, Online
Period	26/05/21 → 28/05/21

Keywords

artificial intelligence
deep-learning models
face emotion recognition
face gesture classification
face images

Access to Document

10.1109/ColCACI52978.2021.9469528

Cite this

Espinel, A., Pérez, N., Riofrío, D., Benítez, D., & Moyano, R. F. (2021). Face Gesture Recognition Using Deep-Learning Models. In A. D. Orjuela-Canon (Ed.), 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings Article 9469528 (2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ColCACI52978.2021.9469528

Espinel, Andrés ; Pérez, Noel ; Riofrío, Daniel et al. / Face Gesture Recognition Using Deep-Learning Models. 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings. editor / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings).

@inproceedings{8fbe7dbb14394ec883977b63e402ccf8,

title = "Face Gesture Recognition Using Deep-Learning Models",

abstract = "This work compares face gesture recognition methods based on deep learning convolutional neural network (DCNN) architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing datasets. We validated the proposed architectures on three different databases: Jaffe, CK+, and the combination of both databases (Jaffe CK+) over a five-fold cross-validation strategy. The DCNN4, DCNN2, and DCNN+Autoencoder models achieved best performance mean accuracy scores of 95\%, 94\%, and 96\% for the Jaffe, CK+, and Jaffe CK+ databases, respectively. Moreover, according to the cross-entropy loss function, the selected models 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 Diego Ben{\'i}tez and Moyano, \{Ricardo Flores\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 ; Conference date: 26-05-2021 Through 28-05-2021",

year = "2021",

month = may,

day = "26",

doi = "10.1109/ColCACI52978.2021.9469528",

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

series = "2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings",

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

editor = "Orjuela-Canon, \{Alvaro David\}",

booktitle = "2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings",

}

Espinel, A, Pérez, N , Riofrío, D , Benítez, D & Moyano, RF 2021, Face Gesture Recognition Using Deep-Learning Models. in AD Orjuela-Canon (ed.), 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings., 9469528, 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021, Virtual, Online, Colombia, 26/05/21. https://doi.org/10.1109/ColCACI52978.2021.9469528

Face Gesture Recognition Using Deep-Learning Models. / Espinel, Andrés; Pérez, Noel ; Riofrío, Daniel et al.
2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings. ed. / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2021. 9469528 (2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings).

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

TY - GEN

T1 - Face Gesture Recognition Using Deep-Learning Models

AU - Espinel, Andrés

AU - Pérez, Noel

AU - Riofrío, Daniel

AU - Benítez, Diego

AU - Moyano, Ricardo Flores

PY - 2021/5/26

Y1 - 2021/5/26

N2 - This work compares face gesture recognition methods based on deep learning convolutional neural network (DCNN) architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing datasets. We validated the proposed architectures on three different databases: Jaffe, CK+, and the combination of both databases (Jaffe CK+) over a five-fold cross-validation strategy. The DCNN4, DCNN2, and DCNN+Autoencoder models achieved best performance mean accuracy scores of 95%, 94%, and 96% for the Jaffe, CK+, and Jaffe CK+ databases, respectively. Moreover, according to the cross-entropy loss function, the selected models did not incur overfitting.

AB - This work compares face gesture recognition methods based on deep learning convolutional neural network (DCNN) architectures named DCNN1, DCNN2, DCNN3, DCNN4, and DCNN+Autoencoder, that maximize the classification performance on single and mixing datasets. We validated the proposed architectures on three different databases: Jaffe, CK+, and the combination of both databases (Jaffe CK+) over a five-fold cross-validation strategy. The DCNN4, DCNN2, and DCNN+Autoencoder models achieved best performance mean accuracy scores of 95%, 94%, and 96% for the Jaffe, CK+, and Jaffe CK+ databases, respectively. Moreover, according to the cross-entropy loss function, the selected models did not incur overfitting.

KW - artificial intelligence

KW - deep-learning models

KW - face emotion recognition

KW - face gesture classification

KW - face images

UR - https://www.scopus.com/pages/publications/85114212482

U2 - 10.1109/ColCACI52978.2021.9469528

DO - 10.1109/ColCACI52978.2021.9469528

M3 - Contribución a la conferencia

AN - SCOPUS:85114212482

T3 - 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings

BT - 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings

A2 - Orjuela-Canon, Alvaro David

PB - Institute of Electrical and Electronics Engineers Inc.

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

Y2 - 26 May 2021 through 28 May 2021

ER -

Espinel A, Pérez N , Riofrío D , Benítez D , Moyano RF. Face Gesture Recognition Using Deep-Learning Models. In Orjuela-Canon AD, editor, 2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. 9469528. (2021 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2021 - Proceedings). doi: 10.1109/ColCACI52978.2021.9469528

Face Gesture Recognition Using Deep-Learning Models

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this