Exploring facial expressions and action unit domains for Parkinson detection
Background and objective
Patients suffering from Parkinson’s disease (PD) present a reduction in facial movements called hypomimia. In this work, we propose to use machine learning facial expression analysis from face images based on action unit domains to improve PD detection. We propose different domain adaptation techniques to exploit the latest advances in automatic face analysis and face action unit detection.
Methods
Three different approaches are explored to model facial expressions of PD patients: (i) face analysis using single frame images and also using sequences of images, (ii) transfer learning from face analysis to action units recognition, and (iii) triplet-loss functions to improve the automatic classification between patients and healthy subjects.
Results
Real face images from PD patients show that it is possible to properly model elicited facial expressions using image sequences (neutral, onset-transition, apex, offset-transition, and neutral) with accuracy improvements of up to 5.5% (from 72.9% to 78.4%) with respect to single-image PD detection. We also show that our proposed action unit domain adaptation provides improvements of up to 8.9% (from 78.4% to 87.3%) with respect to face analysis. Finally, we also show that triplet-loss functions provide improvements of up to 3.6% (from 78.8% to 82.4%) with respect to action unit domain adaptation applied upon models created from scratch. The code of the experiments is available at
Conclusions
Domain adaptation via transfer learning methods seem to be a promising strategy to model hypomimia in PD patients. Considering the good results and also the fact that only up to five images per participant are considered in each sequence, we believe that this work is a step forward in the development of inexpensive computational systems suitable to model and quantify problems of PD patients in their facial expressions.
Top-30
Journals
|
1
2
3
|
|
|
IEEE Access
3 publications, 15%
|
|
|
Computer Methods and Programs in Biomedicine
1 publication, 5%
|
|
|
Cognitive Systems Research
1 publication, 5%
|
|
|
Journal of Speech, Language, and Hearing Research
1 publication, 5%
|
|
|
Lecture Notes in Computer Science
1 publication, 5%
|
|
|
IEEE Journal of Biomedical and Health Informatics
1 publication, 5%
|
|
|
Virtual Reality & Intelligent Hardware
1 publication, 5%
|
|
|
Diagnostics
1 publication, 5%
|
|
|
ACM Computing Surveys
1 publication, 5%
|
|
|
PLoS ONE
1 publication, 5%
|
|
|
npj Parkinson s Disease
1 publication, 5%
|
|
|
Parkinsonism and Related Disorders
1 publication, 5%
|
|
|
Artificial Intelligence Review
1 publication, 5%
|
|
|
Frontiers in Medical Technology
1 publication, 5%
|
|
|
Biomedical Signal Processing and Control
1 publication, 5%
|
|
|
Pattern Recognition
1 publication, 5%
|
|
|
1
2
3
|
Publishers
|
1
2
3
4
5
6
|
|
|
Elsevier
6 publications, 30%
|
|
|
Institute of Electrical and Electronics Engineers (IEEE)
6 publications, 30%
|
|
|
Springer Nature
3 publications, 15%
|
|
|
American Speech Language Hearing Association
1 publication, 5%
|
|
|
MDPI
1 publication, 5%
|
|
|
Association for Computing Machinery (ACM)
1 publication, 5%
|
|
|
Public Library of Science (PLoS)
1 publication, 5%
|
|
|
Frontiers Media S.A.
1 publication, 5%
|
|
|
1
2
3
4
5
6
|
- We do not take into account publications without a DOI.
- Statistics recalculated weekly.