Quantitative analysis of facial paralysis using local binary patterns in biomedical videos

Shu He, J.J. Soraghan, Brian O'Reilly, D. Xing

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

Facial paralysis is the loss of voluntary muscle movement of one side of the face. A quantitative, objective, and reliable assessment system would be an invaluable tool for clinicians treating patients with this condition. This paper presents a novel framework for objective measurement of facial paralysis. The motion information in the horizontal and vertical directions and the appearance features on the apex frames are extracted based on the local binary patterns (LBPs) on the temporal-spatial domain in each facial region. These features are temporally and spatially enhanced by the application of novel block processing schemes. A multiresolution extension of uniform LBP is proposed to efficiently combine the micropatterns and large-scale patterns into a feature vector. The symmetry of facial movements is measured by the resistor-average distance (RAD) between LBP features extracted from the two sides of the face. Support vector machine is applied to provide quantitative evaluation of facial paralysis based on the House-Brackmann (H-B) scale. The proposed method is validated by experiments with 197 subject videos, which demonstrates its accuracy and efficiency.
LanguageEnglish
Pages1864-1870
Number of pages7
JournalIEEE Transactions on Biomedical Engineering
Volume56
Issue number7
DOIs
Publication statusPublished - Jul 2009

Fingerprint

Resistors
Support vector machines
Muscle
Processing
Chemical analysis
Experiments

Keywords

  • biomechanics
  • biomedical measurement
  • feature extraction
  • image motion analysis
  • medical disorders
  • medical image processing
  • muscle
  • neurophysiology
  • patient treatment
  • pattern classification
  • support vector machines
  • video signal processing

Cite this

@article{13659188ba19417986f7e3663150ae9e,
title = "Quantitative analysis of facial paralysis using local binary patterns in biomedical videos",
abstract = "Facial paralysis is the loss of voluntary muscle movement of one side of the face. A quantitative, objective, and reliable assessment system would be an invaluable tool for clinicians treating patients with this condition. This paper presents a novel framework for objective measurement of facial paralysis. The motion information in the horizontal and vertical directions and the appearance features on the apex frames are extracted based on the local binary patterns (LBPs) on the temporal-spatial domain in each facial region. These features are temporally and spatially enhanced by the application of novel block processing schemes. A multiresolution extension of uniform LBP is proposed to efficiently combine the micropatterns and large-scale patterns into a feature vector. The symmetry of facial movements is measured by the resistor-average distance (RAD) between LBP features extracted from the two sides of the face. Support vector machine is applied to provide quantitative evaluation of facial paralysis based on the House-Brackmann (H-B) scale. The proposed method is validated by experiments with 197 subject videos, which demonstrates its accuracy and efficiency.",
keywords = "biomechanics, biomedical measurement, feature extraction, image motion analysis, medical disorders, medical image processing, muscle, neurophysiology, patient treatment, pattern classification, support vector machines, video signal processing",
author = "Shu He and J.J. Soraghan and Brian O'Reilly and D. Xing",
year = "2009",
month = "7",
doi = "10.1109/TBME.2009.2017508",
language = "English",
volume = "56",
pages = "1864--1870",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
number = "7",

}

Quantitative analysis of facial paralysis using local binary patterns in biomedical videos. / He, Shu; Soraghan, J.J.; O'Reilly, Brian; Xing, D.

In: IEEE Transactions on Biomedical Engineering, Vol. 56, No. 7, 07.2009, p. 1864-1870.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Quantitative analysis of facial paralysis using local binary patterns in biomedical videos

AU - He, Shu

AU - Soraghan, J.J.

AU - O'Reilly, Brian

AU - Xing, D.

PY - 2009/7

Y1 - 2009/7

N2 - Facial paralysis is the loss of voluntary muscle movement of one side of the face. A quantitative, objective, and reliable assessment system would be an invaluable tool for clinicians treating patients with this condition. This paper presents a novel framework for objective measurement of facial paralysis. The motion information in the horizontal and vertical directions and the appearance features on the apex frames are extracted based on the local binary patterns (LBPs) on the temporal-spatial domain in each facial region. These features are temporally and spatially enhanced by the application of novel block processing schemes. A multiresolution extension of uniform LBP is proposed to efficiently combine the micropatterns and large-scale patterns into a feature vector. The symmetry of facial movements is measured by the resistor-average distance (RAD) between LBP features extracted from the two sides of the face. Support vector machine is applied to provide quantitative evaluation of facial paralysis based on the House-Brackmann (H-B) scale. The proposed method is validated by experiments with 197 subject videos, which demonstrates its accuracy and efficiency.

AB - Facial paralysis is the loss of voluntary muscle movement of one side of the face. A quantitative, objective, and reliable assessment system would be an invaluable tool for clinicians treating patients with this condition. This paper presents a novel framework for objective measurement of facial paralysis. The motion information in the horizontal and vertical directions and the appearance features on the apex frames are extracted based on the local binary patterns (LBPs) on the temporal-spatial domain in each facial region. These features are temporally and spatially enhanced by the application of novel block processing schemes. A multiresolution extension of uniform LBP is proposed to efficiently combine the micropatterns and large-scale patterns into a feature vector. The symmetry of facial movements is measured by the resistor-average distance (RAD) between LBP features extracted from the two sides of the face. Support vector machine is applied to provide quantitative evaluation of facial paralysis based on the House-Brackmann (H-B) scale. The proposed method is validated by experiments with 197 subject videos, which demonstrates its accuracy and efficiency.

KW - biomechanics

KW - biomedical measurement

KW - feature extraction

KW - image motion analysis

KW - medical disorders

KW - medical image processing

KW - muscle

KW - neurophysiology

KW - patient treatment

KW - pattern classification

KW - support vector machines

KW - video signal processing

U2 - 10.1109/TBME.2009.2017508

DO - 10.1109/TBME.2009.2017508

M3 - Article

VL - 56

SP - 1864

EP - 1870

JO - IEEE Transactions on Biomedical Engineering

T2 - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 7

ER -