Automatic motion feature extraction with application to quantitative assessment of facial paralysis

Shu He, John Soraghan, Brian F O'Reilly

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

4 Citations (Scopus)

Abstract

This paper presents a robust, objective, automated and quantitative assessment system for Facial Paralysis using artificial intelligence analysis of biomedial video data. Facial feature localization and prescribed facial movements detection are discussed. Optical flow is used to obtain the motion features in the relevant facial regions. Radial Basis Function (RBF) Neural Network is applied to provide quantitative evaluation of Facial Paralysis based on the House-Brackmann Scale. The results from 197 videos of 87 subjects are encouraging with a Mean Squared Error (MSE) of 0.013 (training) and 0.0169 (testing).
Original languageEnglish
Title of host publication2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings
Place of PublicationNew York
PublisherIEEE
Pages441-444
Number of pages4
ISBN (Print)9781424407286
DOIs
Publication statusPublished - 2007
Event2007 IEEE International Conference on Acoustics, Speech and Signal Processing - Honolulu, United States
Duration: 15 Apr 200720 Apr 2007

Publication series

NameInternational Conference on Acoustics Speech and Signal Processing (ICASSP)
PublisherIEEE
ISSN (Print)1520-6149

Conference

Conference2007 IEEE International Conference on Acoustics, Speech and Signal Processing
CountryUnited States
CityHonolulu
Period15/04/0720/04/07

Fingerprint

Optical flows
Artificial intelligence
Feature extraction
Neural networks
Testing

Keywords

  • House-Brackmann scale
  • facial paralysis measurement
  • optical flow
  • RBF neural network

Cite this

He, S., Soraghan, J., & O'Reilly, B. F. (2007). Automatic motion feature extraction with application to quantitative assessment of facial paralysis. In 2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings (pp. 441-444). (International Conference on Acoustics Speech and Signal Processing (ICASSP) ). New York: IEEE. https://doi.org/10.1109/ICASSP.2007.366711
He, Shu ; Soraghan, John ; O'Reilly, Brian F. / Automatic motion feature extraction with application to quantitative assessment of facial paralysis. 2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings. New York : IEEE, 2007. pp. 441-444 (International Conference on Acoustics Speech and Signal Processing (ICASSP) ).
@inproceedings{57eb86909908416b93931cc4a39d8515,
title = "Automatic motion feature extraction with application to quantitative assessment of facial paralysis",
abstract = "This paper presents a robust, objective, automated and quantitative assessment system for Facial Paralysis using artificial intelligence analysis of biomedial video data. Facial feature localization and prescribed facial movements detection are discussed. Optical flow is used to obtain the motion features in the relevant facial regions. Radial Basis Function (RBF) Neural Network is applied to provide quantitative evaluation of Facial Paralysis based on the House-Brackmann Scale. The results from 197 videos of 87 subjects are encouraging with a Mean Squared Error (MSE) of 0.013 (training) and 0.0169 (testing).",
keywords = "House-Brackmann scale , facial paralysis measurement , optical flow, RBF neural network",
author = "Shu He and John Soraghan and O'Reilly, {Brian F}",
year = "2007",
doi = "10.1109/ICASSP.2007.366711",
language = "English",
isbn = "9781424407286",
series = "International Conference on Acoustics Speech and Signal Processing (ICASSP)",
publisher = "IEEE",
pages = "441--444",
booktitle = "2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings",

}

He, S, Soraghan, J & O'Reilly, BF 2007, Automatic motion feature extraction with application to quantitative assessment of facial paralysis. in 2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings. International Conference on Acoustics Speech and Signal Processing (ICASSP) , IEEE, New York, pp. 441-444, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, United States, 15/04/07. https://doi.org/10.1109/ICASSP.2007.366711

Automatic motion feature extraction with application to quantitative assessment of facial paralysis. / He, Shu; Soraghan, John; O'Reilly, Brian F.

2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings. New York : IEEE, 2007. p. 441-444 (International Conference on Acoustics Speech and Signal Processing (ICASSP) ).

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Automatic motion feature extraction with application to quantitative assessment of facial paralysis

AU - He, Shu

AU - Soraghan, John

AU - O'Reilly, Brian F

PY - 2007

Y1 - 2007

N2 - This paper presents a robust, objective, automated and quantitative assessment system for Facial Paralysis using artificial intelligence analysis of biomedial video data. Facial feature localization and prescribed facial movements detection are discussed. Optical flow is used to obtain the motion features in the relevant facial regions. Radial Basis Function (RBF) Neural Network is applied to provide quantitative evaluation of Facial Paralysis based on the House-Brackmann Scale. The results from 197 videos of 87 subjects are encouraging with a Mean Squared Error (MSE) of 0.013 (training) and 0.0169 (testing).

AB - This paper presents a robust, objective, automated and quantitative assessment system for Facial Paralysis using artificial intelligence analysis of biomedial video data. Facial feature localization and prescribed facial movements detection are discussed. Optical flow is used to obtain the motion features in the relevant facial regions. Radial Basis Function (RBF) Neural Network is applied to provide quantitative evaluation of Facial Paralysis based on the House-Brackmann Scale. The results from 197 videos of 87 subjects are encouraging with a Mean Squared Error (MSE) of 0.013 (training) and 0.0169 (testing).

KW - House-Brackmann scale

KW - facial paralysis measurement

KW - optical flow

KW - RBF neural network

U2 - 10.1109/ICASSP.2007.366711

DO - 10.1109/ICASSP.2007.366711

M3 - Conference contribution book

SN - 9781424407286

T3 - International Conference on Acoustics Speech and Signal Processing (ICASSP)

SP - 441

EP - 444

BT - 2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings

PB - IEEE

CY - New York

ER -

He S, Soraghan J, O'Reilly BF. Automatic motion feature extraction with application to quantitative assessment of facial paralysis. In 2007 IEEE International conference on acoustics, speech and signal processing, Volume I, Parts 1-3, Proceedings. New York: IEEE. 2007. p. 441-444. (International Conference on Acoustics Speech and Signal Processing (ICASSP) ). https://doi.org/10.1109/ICASSP.2007.366711