3DBODY.TECH 2022 - Paper 22.44

A. Agostini et al., "Reliability and Accuracy of Mobile 3D Scanning Technologies for the Customization of Respiratory Face Masks", Proc. of 3DBODY.TECH 2022 - 13th Int. Conf. and Exh. on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 25-26 Oct. 2022, #44, https://doi.org/10.15221/22.44.


Reliability and Accuracy of Mobile 3D Scanning Technologies for the Customization of Respiratory Face Masks


Arthur AGOSTINI 1,2, Aude CASTONGUAY-HENRI 1, Sean-Philippe VIENS 1, Jonathan BORDUAS 1, Luc DUONG 2

1 Technologies Shapeshift 3D Inc., Montreal (QC), Canada;
2 Ecole de Technologie Superieure, Montreal (QC), Canada


This article compares the reliability and accuracy of face-scanning technologies used in the context of head reconstruction. The goal of this study is to provide recommendations as to which technology is suitable for customizing respiratory face masks. Two technologies will be analyzed; ARKit: Face Tracking SDK by Apple using an iPhone XR, and Structure Sensor by Occipital using the 3DSizeMe app with an iPad Pro 5th generation. As ARKit only generates a mesh on the face, the Flame AI framework is used to extrapolate the full head shape.
Reliability and accuracy were determined through a series of standard measurements taken on each reconstructed scan of a series of 48 male and female retopologised head scans obtained from the 3D Scan Store. Each head was 3D printed and scanned three times with both ARKit and the Structure Sensor. A deep-learning model was used to identify 73 standard landmarks on each face from which were derived 11 anthropometric measurements defined by the ISO 16976-2:2015 part 2. The anthropometric measurements were compared between scans of a single face for reliability and compared with the initial head form for accuracy.
Context: In 2021, the production of off-the-shelf single-use N95 masks had almost quintupled since the Covid-19 outbreak in 2019. Healthcare professionals must now wear a mask at all times when treating patients. They thus wear masks every day for extensive periods of time. The airtight seal required to guarantee efficiency sometimes requires excessive pressure depending on the morphology. This, coupled with the prolonged use, often causes discomfort and injuries. This issue led to a worldwide effort to develop custom-fitted respiratory masks. The advantage of designing a custom-made mask based on the 3D scan of the face is ergonomic and improves user comfort over extended periods of time.


Digital anthropometry, 3D reconstruction, 3D scanning, Anthropometric measurements, Accuracy, Reliability, Cloud computing, 3D Face scan, 3D Head scan, Custom fit, Machine learning, Mobile devices, COVID-19, Respiratory Mask.


Full paper: 2244agostini.pdf
Proceedings: 3DBODY.TECH 2022, 25-26 Oct. 2022, Lugano, Switzerland
Paper id#: 44
DOI: 10.15221/22.44
Presentation video: 3DBodyTech2022_44_agostini.mp4

Copyright notice

© Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Reproduction of the proceedings or any parts thereof (excluding short quotations for the use in the preparation of reviews and technical and scientific papers) may be made only after obtaining the specific approval of the publisher. The papers appearing in the proceedings reflect the author's opinions. Their inclusion in these publications does not necessary constitute endorsement by the editor or by the publisher. Authors retain all rights to individual papers.

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