Classification analysis of young female students’ waist–abdomen–hip based on body photos

Abstract

To improve body-type classification research and personalized clothing, this study adopted a research method of “three-dimensional (3D) scanning + photos” for the body-shape classification of young females’ waist–abdomen–hip. A total of 178 female college students were recruited for manual, photo and 3D body measurement to get the main body information. Based on the data acquired from 3D scanning, the corresponding heights, angles and other parameters of the waist, abdomen and hip were selected and used to analyze the human body in two respects of shape and height. Then the body-shape indexes and the height indexes were respectively analyzed, and 16 shape characteristic indicators and four height characteristic parameters affecting the waist, abdomen and hip were extracted. Three types in shape and two types in height were obtained, and the main classification rules of the waist–abdomen–hip shape were also concluded to identify the body type based on the body measurements extracted from body photos, which realized the automatic body-type identification based on body photos. It was of great practical significance to provide a basis for personalized customization of fast clothing and the subdivision of the human body shape, which could meet the individual customer’s requirements.

Automatic recognition of the neck–shoulder shape based on 2D photos

“…As for the 3D method, [TC] 2 3D body scanner (model NX-16, with an accuracy of 0.6 mm) made in the USA was used to obtain the point-cloud data information. 28…”

“…As for the 3D method, [TC] 2 3D body scanner (model NX-16, with an accuracy of 0.6 mm) made in the USA was used to obtain the point-cloud data information. 28 During the measuring procedure of the two methods, the subjects should wear light-colored and fitted clothes without any accessory to reduce the influence of the wearing and standing posture. The subjects should also wear a tight-fitting swimming hat, which can completely cover the hair, which is shown in Figure 2.…”

Classification of female body shape based on two-dimensional image and computer vision technology

“…Wang and Gu 19 used the 3D point cloud data of young females to classify the neck-shoulder part of the human body by selecting the back angle, shoulder angle, armpit depth/width ratio, and shoulder depth/ width ratio, and then realized the automatic identification of the neck and shoulder shape based on 2D photos of young females. Cai et al 20 used a method of "3D scanning þ photos" for the body shape classification of young females' waist-abdomen-hip. These methods represent the embryonic form of 2D image body shape classification and discrimination, but they are still based on the human body size.…”

“…Cai et al. 20 used a method of “3D scanning + photos” for the body shape classification of young females’ waist–abdomen–hip. These methods represent the embryonic form of 2D image body shape classification and discrimination, but they are still based on the human body size.…”