Related Experiment Video
Updated: Jun 24, 2026
10:28
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
Published on: July 24, 2019
Quantitative analysis of facial paralysis using local binary patterns in biomedical videos
Shu He1, John J Soraghan, Brian F O'Reilly
1Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XQ, UK. shu.he@eee.strath.ac.uk
IEEE Transactions on Bio-Medical Engineering
|April 2, 2009
Summary
This study introduces a new objective system for measuring facial paralysis. The framework uses local binary patterns to analyze facial movements, providing accurate and efficient quantitative evaluations for clinical use.
Area of Science:
- Biomedical Engineering
- Computer Vision
- Medical Imaging
Background:
- Facial paralysis significantly impacts quality of life.
- Current assessment methods for facial paralysis lack objectivity and reliability.
- An objective measurement system is crucial for effective clinical management.
Purpose of the Study:
- To develop a novel framework for the objective measurement of facial paralysis.
- To provide a quantitative and reliable assessment tool for clinicians.
- To correlate objective measurements with the established House-Brackmann scale.
Main Methods:
- Extraction of temporal-spatial features using local binary patterns (LBPs) in facial regions.
- Enhancement of features via novel block processing schemes.
- Measurement of facial symmetry using resistor-average distance (RAD) between contralateral facial regions.
- Quantitative evaluation using Support Vector Machine (SVM) based on the House-Brackmann (H-B) scale.
Main Results:
- The proposed framework accurately quantifies facial paralysis.
- Experimental validation with 197 subject videos demonstrates high accuracy and efficiency.
- The system provides objective data correlating with clinical grading scales.
Conclusions:
- The novel framework offers an accurate and efficient method for objective facial paralysis assessment.
- This tool can aid clinicians in treatment planning and outcome evaluation.
- The approach enhances the reliability of facial paralysis diagnosis and monitoring.
