Product sizing with 3D anthropometry and<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si4.gif" display="inline" id="mml4" overflow="scroll"><mml:mi>k</mml:mi></mml:math>-medoids clustering

Lacko, Daniël; Huysmans, Toon; Vleugels, Jochen; Bruyne, Guido De; Hulle, Marc M. Van; Sijbers, Jan; Verwulgen, Stijn

doi:10.1016/j.cad.2017.06.004

Cited by 35 publications

(19 citation statements)

References 20 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering methods have been used to determine product sizes in previous work [10,12,13]. A K-means clustering method was utilized (SPSS version 22) in order to divide the sample into four clusters that represent the variation of the childrens faces.…”

Section: Clustering and Rfm Developmentmentioning

confidence: 99%

A Comparison Between Representative 3D Faces Based on Bi- and Multi-variate and Shape Based Analysis

Goto

Huysmans

Lee

et al. 2018

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

In Ergonomic product design, designers need to translate anthropometric data of the target population into product dimensions or sizing systems. Currently, sizing systems are often based on traditional anthropometric data and generally use the variation of one or two key body dimensions directly related to the product. For products that need to closely fit a certain part of the body it is relevant to incorporate multiple key dimensions. This can be realized by a multivariate approach such as a Principal Component Analysis. Over the past decades, there has been an increase in incorporating 3D imaging in anthropometric surveys. In order to integrate the use of 3D anthropometry in product sizing, representative models are used to visualize the variability of the target population. For the development of a ventilation mask for children, this study compares representative models of 3D faces based on a bivariate, multivariate and shape based analysis of 303 children's faces.

show abstract

Section: Clustering and Rfm Developmentmentioning

confidence: 99%

A Comparison Between Representative 3D Faces Based on Bi- and Multi-variate and Shape Based Analysis

Goto

Huysmans

Lee

et al. 2018

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In medicine, examples of usage can be found in spine deformation detection [1,2], CT/MRI image analysis [3] or maxillo-facial diagnosis [4]. Other applications relate to, e.g., the skeleton rig processing for animation [5], motion capture [6], and human system engineering in the clothing industry [7,8]. All applications above focus on measurements and their accuracy.…”

Section: Introductionmentioning

confidence: 99%

Algorithm for Detecting Characteristic Points on a Three-Dimensional, Whole-Body Human Scan

2020

View full text Add to dashboard Cite

Anthropometric landmarks obtained from three-dimensional (3D) body scans are widely used in medicine, civil engineering, and virtual reality. For all those fields, an acquisition of certain and accurate landmark positions is crucial for obtaining satisfying results. Manual marking is time-consuming and is affected by the subjectivity of the human operator. Therefore, an automatic approach has become increasingly popular. This paper provides a short survey of different attempts for automatic landmark localization, from which one machine learning-based method was further analyzed and extended in the case of input data preparation for a convolutional neural network (CNN). A novel method of data processing is presented which utilize a mid-surface projection followed by further unwrapping. The article emphasizes its significance and the way it affects the outcome of a deep neural network. The workflow and the detailed description of algorithms used are included in this paper. To validate the method, it was compared with the orthogonal projection used for the state-of-the-art approach. Datasets consisting of 200 specimens, acquired using both methods, were used for convolutional neural networks training and 20 for validation. In this paper, we used YOLO v.3 architecture for detection and ResNet-152 for classification. For each approach, localizations of 22 normalized body landmarks for 10 male and 10 female subjects of different ages and various postures were obtained. To compare the accuracy of approaches, errors and their distribution were measured for each characteristic point. Experiments confirmed that the mid-surface projections resulted, on average, in a 14% accuracy improvement and up to 15% enhancement of resistance on errors related to scan imperfections.

show abstract

“…The performance of feature based, shape based and feature-constrained shape based clustering was compared in an enriched SSM of the head (46). Feature based clustering preformed significantly worse that shape based and feature-constrained shape based clustering.…”

Section: Potential For Fit Within Clustersmentioning

confidence: 99%

“…This is usually the center, mean or medoid along the dissimilarity metric. Enriched SSMs allow three clustering methods that are of interest in product development (46).…”

Section: Enriched Ssms For Fit Within Clustersmentioning

confidence: 99%

A new data structure and workflow for using 3D anthropometry in the design of wearable products

Verwulgen

Lacko

Vleugels

et al. 2018

International Journal of Industrial Ergonomics

Self Cite

View full text Add to dashboard Cite

Abstract.The human body is a complex biomechanical system that exhibits many variations. Wearable products should be both functional and comfortable. They require a close and accurate fit to the body of the end-user. Current approaches to design body near products rely on 1D anthropometry and unrealistic manikins, e.g. constructed from simple surfaces such as spheres and cylinders connected by splines. With the uprising of 3D scanning, a myriad of accurate 3D body models becomes available. In this paper we present a framework to use this 3D shape information in the development of wearable products. The key concept that we introduce to achieve this extension, is an enriched shape model: a statistical shape model of the human body that also contains all 1D anthropometric data in it. With enriched shape models, a 3D shape can be parameterized with a given set of anthropometric features. Thus the dense geometric information of an individual's shape can be obtained simply by tuning that individual's anthropometric values. By designing on the generated 3D surface, a product can be obtained that closely fits the individual's shape. We thus extend the method of linking 1D anthropometric data with the dimensions of a product. This results in three design strategies that link both body shape with product geometry: design for collective fit, design for fit within clusters and design for individual fit. Each strategy is explained and studied with the design of wearable EEG headsets that fits the human head. KeywordsMass-customization, EEG headsets, CAD, parameterized design, 3D anthropometry, statistical shape models Relevance to Design PracticeWe present a workflow to use accurate 3D shape models of the human body in the design of products that should closely fit the end-user. To that end, we introduce enriched shape models: a new data structure that contains all dense geometric shape information together with classical anthropometric data. We illustrate how enriched shape models can be used to achieve products with personalized fit, as an extension to the use of univariate anthropometric data. The use of enriched shape models for personalized design could become an important driver for mass customization. To that end, tools and techniques should be developed to incorporate the presented workflow in CAD/CAM.

show abstract

Product sizing with 3D anthropometry andk-medoids clustering

Cited by 35 publications

References 20 publications

A Comparison Between Representative 3D Faces Based on Bi- and Multi-variate and Shape Based Analysis

A Comparison Between Representative 3D Faces Based on Bi- and Multi-variate and Shape Based Analysis

Algorithm for Detecting Characteristic Points on a Three-Dimensional, Whole-Body Human Scan

A new data structure and workflow for using 3D anthropometry in the design of wearable products

Contact Info

Product

Resources

About