Predicting 3D lip shapes using facial surface EMG

Merijn Eskes, Maarten J.A. Van Alphen, Alfons J.M. Balm, Ludi E. Smeele, Dieta Brandsma, Ferdinand Van Der Heijden

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)
40 Downloads (Pure)

Abstract

Aim: The aim of this study is to prove that facial surface electromyography (sEMG) conveys sufficient information to predict 3D lip shapes. High sEMG predictive accuracy implies we could train a neural control model for activation of biomechanical models by simultaneously recording sEMG signals and their associated motions.

Materials and methods: With a stereo camera set-up, we recorded 3D lip shapes and simultaneously performed sEMG measurements of the facial muscles, applying principal component analysis (PCA) and a modified general regression neural network (GRNN) to link the sEMG measurements to 3D lip shapes. To test reproducibility, we conducted our experiment on five volunteers, evaluating several sEMG features and window lengths in unipolar and bipolar configurations in search of the optimal settings for facial sEMG.

Conclusions: The errors of the two methods were comparable. We managed to predict 3D lip shapes with a mean accuracy of 2.76 mm when using the PCA method and 2.78 mm when using modified GRNN. Whereas performance improved with shorter window lengths, feature type and configuration had little influence.
Original languageEnglish
Article numbere0175025
JournalPLoS ONE
Volume12
Issue number4
DOIs
Publication statusPublished - 1 Apr 2017

Fingerprint

Electromyography
electromyography
lips
Lip
Principal Component Analysis
Principal component analysis
neural networks
principal component analysis
Facial Muscles
Neural networks
cameras
reproducibility
volunteers
Muscle
Volunteers
Chemical activation
methodology
Cameras
muscles

Cite this

Eskes, M., Van Alphen, M. J. A., Balm, A. J. M., Smeele, L. E., Brandsma, D., & Van Der Heijden, F. (2017). Predicting 3D lip shapes using facial surface EMG. PLoS ONE, 12(4), [e0175025]. https://doi.org/10.1371/journal.pone.0175025
Eskes, Merijn ; Van Alphen, Maarten J.A. ; Balm, Alfons J.M. ; Smeele, Ludi E. ; Brandsma, Dieta ; Van Der Heijden, Ferdinand. / Predicting 3D lip shapes using facial surface EMG. In: PLoS ONE. 2017 ; Vol. 12, No. 4.
@article{d30c1a84ed2b43b3a21ec87fa707855b,
title = "Predicting 3D lip shapes using facial surface EMG",
abstract = "Aim: The aim of this study is to prove that facial surface electromyography (sEMG) conveys sufficient information to predict 3D lip shapes. High sEMG predictive accuracy implies we could train a neural control model for activation of biomechanical models by simultaneously recording sEMG signals and their associated motions.Materials and methods: With a stereo camera set-up, we recorded 3D lip shapes and simultaneously performed sEMG measurements of the facial muscles, applying principal component analysis (PCA) and a modified general regression neural network (GRNN) to link the sEMG measurements to 3D lip shapes. To test reproducibility, we conducted our experiment on five volunteers, evaluating several sEMG features and window lengths in unipolar and bipolar configurations in search of the optimal settings for facial sEMG. Conclusions: The errors of the two methods were comparable. We managed to predict 3D lip shapes with a mean accuracy of 2.76 mm when using the PCA method and 2.78 mm when using modified GRNN. Whereas performance improved with shorter window lengths, feature type and configuration had little influence.",
author = "Merijn Eskes and {Van Alphen}, {Maarten J.A.} and Balm, {Alfons J.M.} and Smeele, {Ludi E.} and Dieta Brandsma and {Van Der Heijden}, Ferdinand",
year = "2017",
month = "4",
day = "1",
doi = "10.1371/journal.pone.0175025",
language = "English",
volume = "12",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

Eskes, M, Van Alphen, MJA, Balm, AJM, Smeele, LE, Brandsma, D & Van Der Heijden, F 2017, 'Predicting 3D lip shapes using facial surface EMG' PLoS ONE, vol. 12, no. 4, e0175025. https://doi.org/10.1371/journal.pone.0175025

Predicting 3D lip shapes using facial surface EMG. / Eskes, Merijn; Van Alphen, Maarten J.A.; Balm, Alfons J.M.; Smeele, Ludi E.; Brandsma, Dieta; Van Der Heijden, Ferdinand.

In: PLoS ONE, Vol. 12, No. 4, e0175025, 01.04.2017.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Predicting 3D lip shapes using facial surface EMG

AU - Eskes, Merijn

AU - Van Alphen, Maarten J.A.

AU - Balm, Alfons J.M.

AU - Smeele, Ludi E.

AU - Brandsma, Dieta

AU - Van Der Heijden, Ferdinand

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Aim: The aim of this study is to prove that facial surface electromyography (sEMG) conveys sufficient information to predict 3D lip shapes. High sEMG predictive accuracy implies we could train a neural control model for activation of biomechanical models by simultaneously recording sEMG signals and their associated motions.Materials and methods: With a stereo camera set-up, we recorded 3D lip shapes and simultaneously performed sEMG measurements of the facial muscles, applying principal component analysis (PCA) and a modified general regression neural network (GRNN) to link the sEMG measurements to 3D lip shapes. To test reproducibility, we conducted our experiment on five volunteers, evaluating several sEMG features and window lengths in unipolar and bipolar configurations in search of the optimal settings for facial sEMG. Conclusions: The errors of the two methods were comparable. We managed to predict 3D lip shapes with a mean accuracy of 2.76 mm when using the PCA method and 2.78 mm when using modified GRNN. Whereas performance improved with shorter window lengths, feature type and configuration had little influence.

AB - Aim: The aim of this study is to prove that facial surface electromyography (sEMG) conveys sufficient information to predict 3D lip shapes. High sEMG predictive accuracy implies we could train a neural control model for activation of biomechanical models by simultaneously recording sEMG signals and their associated motions.Materials and methods: With a stereo camera set-up, we recorded 3D lip shapes and simultaneously performed sEMG measurements of the facial muscles, applying principal component analysis (PCA) and a modified general regression neural network (GRNN) to link the sEMG measurements to 3D lip shapes. To test reproducibility, we conducted our experiment on five volunteers, evaluating several sEMG features and window lengths in unipolar and bipolar configurations in search of the optimal settings for facial sEMG. Conclusions: The errors of the two methods were comparable. We managed to predict 3D lip shapes with a mean accuracy of 2.76 mm when using the PCA method and 2.78 mm when using modified GRNN. Whereas performance improved with shorter window lengths, feature type and configuration had little influence.

UR - http://www.scopus.com/inward/record.url?scp=85017416621&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0175025

DO - 10.1371/journal.pone.0175025

M3 - Article

VL - 12

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 4

M1 - e0175025

ER -

Eskes M, Van Alphen MJA, Balm AJM, Smeele LE, Brandsma D, Van Der Heijden F. Predicting 3D lip shapes using facial surface EMG. PLoS ONE. 2017 Apr 1;12(4). e0175025. https://doi.org/10.1371/journal.pone.0175025