The effect of aging on facial movement and head posing in a five year window
DOI:
https://doi.org/10.14311/CTJ.2026.56.03Abstract
Automated analysis of facial expressivity is a promising tool for the early detection of hypomimia in Parkinson’s disease. However, accurately distinguishing pathological decline from normal aging requires a robust normative baseline. This study aimed to quantify spontaneous facial movement and structural changes in healthy aging over a five-year longitudinal interval. We analyzed video recordings of a minute-long spontaneous speech from 21 healthy individuals (mean age 60.0 ± 9.2 years) at baseline and five-year follow-up sessions using an automated pipeline based on 478 facial landmarks. Longitudinal analysis revealed remarkable stability in facial kinematics, with no significant degradation in dynamic expressivity observed over the five-year window. In contrast, cross-sectional correlation with age identified significant structural changes, specifically reductions in cheek, lateral canthal, and nose root areas, reflecting cumulative muscle tightening and tissue sagging. Furthermore, we identified distinct sexual dimorphism; women exhibited significantly greater mouth openness and mouth movement variability compared to men, with mouth mobility positively correlating with age in the women cohort. We conclude that facial aging is a slow, cumulative process that does not significantly disrupt facial mobility in the short term. Consequently, rapid declines in facial expressivity observed over five-year intervals can be confidently attributed to neurodegeneration rather than typical aging. Our findings underscore the necessity to streamline feature sets to eliminate redundancy and to account for sex and age balance between study groups.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Filip Šlapal, Michal Novotný
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of the first publication with the work simultaneously licensed under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in CTJ.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website or ResearchGate) prior to and during the submission process, as it can lead to productive exchanges.
CTJ requires that all of the content of the manuscript has been created by its respective authors or that permission to use a copyrighted material has been obtained by the authors before submitting the manuscript to CTJ. CTJ requires that authors have not used any copyrighted material illegally, as for example a picture from another journal or book, a photo, etc. It is the author’s responsibility to use only materials not violating the copyright law. When in doubt, CTJ may ask the authors to supply the pertinent permission or agreement about the use of a copyrighted material.
The opinions expressed in CTJ articles are those of authors and do not necessarily reflect the views of the publishers or the Czech Society for Biomedical Engineering and Medical Informatics.
