Performance of a 2D image-based anthropometric measurement and clothing sizing system

Two-dimensional, image-based anthropometric measurement systems offer an in teresting alternative to traditional and three-dimensional methods in appli cations such as clothing sizing. These automated systems are attractive bec ause of their low cost and the speed with which they can measure size and d etermine the best-fitting garment. Although these systems have appeal in th is type of application, not much is known about the accuracy and precision of the measurements they take. In this paper, the performance of one such s ystem was assessed. The accuracy of the system was analyzed using a databas e of 349 subjects (male and female) who were also measured with traditional anthropometric tools and techniques, and the precision was estimated throu gh repeated measurements of both a plastic mannequin and a human subject. T he results of the system were compared with those of trained anthropometris ts, and put in perspective relative to clothing sizing requirements and sho rt-term body changes, It was concluded that image-based systems are capable of providing anthropometric measurements that are quite comparable to trad itional measurement methods (performed by skilled measurers), both in terms of accuracy and repeatability. Crown Copyright (C) 2000 Published by Elsev ier Science Ltd. All rights reserved.