User-Defined Three-Dimensional Human Body Measurement Using Bone Structure and Cluster Analysis 


Vol. 62,  No. 6, pp. 346-352, Dec.  2025
10.12772/TSE.2025.62.346


PDF Full-Text
  Abstract

Recent advancements in deep learning technology have automated human body measurement, particularly the generation of skeletal information. Among various free technologies for generating skeletal information, this study investigated a method to easily obtain diverse human body measurement data using Adobe Mixamo. For the experimental verification, SizeKorea 6th Edition data for 20s women and men with low and high mesh resolutions were used. Landmarks and cross-sectional curves were found based on bilinear interpolation of bone endpoints. Moreover, the system was designed to allow users to define landmarks easily via simple Python-based scripts. Girth sizes and feature vertical positions showed a maximal 10.7% of errors compared to the SizeKorea manual measurement. The errors are mainly from the noise in the clustering process. However, the proposed method had an advantage in that it can be applied to shapes with arbitrary poses.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

설인환, "User-Defined Three-Dimensional Human Body Measurement Using Bone Structure and Cluster Analysis," Textile Science and Engineering, vol. 62, no. 6, pp. 346-352, 2025. DOI: 10.12772/TSE.2025.62.346.

[ACM Style]

설인환. 2025. User-Defined Three-Dimensional Human Body Measurement Using Bone Structure and Cluster Analysis. Textile Science and Engineering, 62, 6, (2025), 346-352. DOI: 10.12772/TSE.2025.62.346.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

pISSN : 1225 - 1089
eISSN : 2288 - 6419

한국연구재단 우수등재학술지 유지 (2022년)