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

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.