Analyzing Body Asymmetry Using 3D Scans and Machine Learning: Insights from Demographic Patterns and Dominant Hand Bias - 25.30

Title:

Analyzing Body Asymmetry Using 3D Scans and Machine Learning: Insights from Demographic Patterns and Dominant Hand Bias

Authors:

Yingying WU 1, Kristen MORRIS 2, Xuebo LIU 1, Reannan BOISVERT 1, Hongyu WU 1

1 Kansas State University, Manhattan, KS, USA;
2 Colorado State University, Fort Collins, CO, USA

Full paper:

The paper has been reviewed and the authors are currently updating it. The full paper will be available shortly as PDF file.

Keywords:

3D body scanning, body asymmetry, machine learning

Abstract:

Accurate body measurements underpin anthropometry, ergonomics, and apparel design, yet practitioners often assume bilateral symmetry and measure only one side. The rationale for this convention is limited. Therefore, this exploratory study aimed at quantifying body asymmetries at various body locations for improving the accuracy of measurement protocols, garment patterns, and ultimately product fit. The researchers analyzed 22 paired measurements derived from three-dimensional body scans of 245 adults. Statistical tests included independent samples t-tests, Pearson correlations, and chi-square tests. The researchers further applied a Support Vector Machine model to examine relationships between asymmetry, demographics, and hand dominance. The results reveal where asymmetries are negligible versus practically meaningful, highlight relationships among body dimensions, and identify demographic and dominance factors associated with asymmetry. Based on these findings, the researchers propose actionable recommendations for refining anthropometric procedures and patternmaking standards, encouraging when bilateral measurements are warranted and when single-side measures suffice.

Presentation:

Video availble in 3DBODY.TECH 2025 Proceedings - 25.30

Details:

Volume/Issue: 3DBODY.TECH Journal - Vol. 2, 2025
Paper: #30
Published: 2025/12/31
Presented at: 3DBODY.TECH 2025, 21-22 Oct. 2025, Lugano, Switzerland
Proceedings: 3DBODY.TECH 2025 Proceedings

License/Copyright notice

Copyright © 2025 by the author(s).
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The papers appearing in the journal reflect the author's opinions. Their inclusion in the volumes does not necessary constitute endorsement by the editor or by the publisher.

Note: click the + on the top left of the page to open/close the menu.