To read the full version of this content please select one of the options below:

The establishment of human body three vital measurements regression relationship based on SVR method

Xiaojiu Li (Institute of Art and Clothing, Tianjin Polytechnic University, Tianjin, China.)
Xiaoning Jing (Tianjin Polytechnic University, Tianjin, China.)

International Journal of Clothing Science and Technology

ISSN: 0955-6222

Article publication date: 2 March 2015

Abstract

Purpose

The purpose of this paper is to obtain circumference sizes from 2D feature sizes in the parts of three vital measurements of young female, the dimensions of chest width, chest depth, waist width, waist depth, hip width, hip depth, chest girth, waist girth and hip girth of 400 young female samples are collected.

Design/methodology/approach

Inside which, 300 samples are used as learning samples, and the remaining 100 samples are used as training samples, the sample data are entered to the network constructed by support vector machine regression (SVR) and the predictive value of circumference sizes are gained.

Findings

Finally, the regression model is established between 2D feature size and the corresponding circumference size. Through the trained prediction model based on SVR, the circumference sizes in three vital measurement parts of a new sample are predicted for convenient mass measurement.

Originality/value

The research of measurement regression relationship in parts of three vital measurements of young female is the basis for conveniently obtaining dimensions in garment mass measurement. It can provide the accurate data to feminine dress industry, and has high precision.

Keywords

Citation

Li, X. and Jing, X. (2015), "The establishment of human body three vital measurements regression relationship based on SVR method", International Journal of Clothing Science and Technology, Vol. 27 No. 1, pp. 148-158. https://doi.org/10.1108/IJCST-11-2013-0125

Publisher

:

Emerald Group Publishing Limited

Copyright © 2015, Emerald Group Publishing Limited