Track

TD

Presentation Type

Event

Description

The purpose of this study is to develop a new body shape classification method using variables measured on the flattened figures of men's body surface. It is designed to reflect the concrete characteristics of the men's formal jacket patterns so that it becomes easy to be utilized for the mass customization of men's formal jacket. 152 men's body scan surfaces were flattened into development figures using automatic flattening software and 17 angles and 2 size differences were measured on the flattened figures. The measured sizes were put into factor analysis and 5 factors are extracted: 'Width and protrusion of hip', 'Anteroposterior position of hip', 'Bending of shoulder', 'Protrusion of chest' and 'Sway back'. K-means clustering were conducted using extracted factor scores and 152 subjects were classified into 5 flattened figure types of 'straight', 'sway back', 'bend forward', 'lean back-b' and 'lea back-I'. An estimation model for the flattened body surface figure types was developed using logistic regression analysis. The agreements between logistic regression model and k-means clustering were 90.8% on average. It became possible to anticipate the specific shapes of flattened body surface figures of the random subjects using the results of this study. It could be applied to the mass customization system and will make it easy to offer the jacket patterns tailored to the individual consumer's body shapes.

Share

COinS
 
Jan 1st, 12:00 AM

Development of Classification Method of the Flattened Body Surface Figures for the Mass Customization of Men's Formal Jacket

The purpose of this study is to develop a new body shape classification method using variables measured on the flattened figures of men's body surface. It is designed to reflect the concrete characteristics of the men's formal jacket patterns so that it becomes easy to be utilized for the mass customization of men's formal jacket. 152 men's body scan surfaces were flattened into development figures using automatic flattening software and 17 angles and 2 size differences were measured on the flattened figures. The measured sizes were put into factor analysis and 5 factors are extracted: 'Width and protrusion of hip', 'Anteroposterior position of hip', 'Bending of shoulder', 'Protrusion of chest' and 'Sway back'. K-means clustering were conducted using extracted factor scores and 152 subjects were classified into 5 flattened figure types of 'straight', 'sway back', 'bend forward', 'lean back-b' and 'lea back-I'. An estimation model for the flattened body surface figure types was developed using logistic regression analysis. The agreements between logistic regression model and k-means clustering were 90.8% on average. It became possible to anticipate the specific shapes of flattened body surface figures of the random subjects using the results of this study. It could be applied to the mass customization system and will make it easy to offer the jacket patterns tailored to the individual consumer's body shapes.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.