Leveraging AI to Examine Diversity in Body Dimensions Through Contrasting 3D Scans with Standardized Forms - 24.14
R. Alhassawi et al., "Leveraging AI to Examine Diversity in Body Dimensions Through Contrasting 3D Scans with Standardized Forms", Proc. of 3DBODY.TECH 2024 - 15th Int. Conf. and Exh. on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 22-23 Oct. 2024, #14.
Title:
Leveraging AI to Examine Diversity in Body Dimensions Through Contrasting 3D Scans with Standardized Forms
Authors:
Ruqey ALHASSAWI, Simeon GILL, Steven HAYES, Kristina BRUBACHER
The University of Manchester, Manchester, UK
Abstract:
This study addresses the challenge of providing well-fitting clothing sizes by using 3D body scanning and machine learning algorithms for improved size prediction. Data from 677 female participants' revealed notable variations in body measurements, emphasizing the need for more anthropometric analysis to better understand existing sizing standards. The research compared basic Support Vector Machine (SVM) models, using key measurements such as bust, waist, and hips, with an enhanced PCA-SVM model incorporating additional body dimensions. The basic SVM achieved higher accuracy (89.66%) than the PCA-SVM (68.97%), suggesting that fewer key measurements provide better predictions. These findings highlight the potential of 3D scanning and SVM models in developing sizing systems that accommodate diverse body types.
Keywords:
anthropometric 3d body scanning, standardized sizing, AI techniques, diversity in body dimensions
Abstract:
Presentation:
VIDEO will be available here in Q3.2025.
VIDEO availble in proceedings (purchase order)
Details:
Proceedings: 3DBODY.TECH 2024, 22-23 Oct. 2024, Lugano, Switzerland
Paper/Presentation: #14
DOI: -
License/Copyright notice
Proceedings: © Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Authors retain all rights to individual papers, which are 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 proceedings reflect the author's opinions. Their inclusion in the proceedings 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.