Body shape classification and block optimization based on space vector length

Abstract

PurposeConsidering two-dimensional features in the body shape classification system cannot fully reflect the three-dimensional (3D) morphological characteristics of human body. The purpose of this paper is to propose a 3D feature based method to characterize and classify the upper body shape of women, and then obtained the corresponding garment block and improved the fitness of clothing.Design/methodology/approachIn this study, the [TC]23D scanner was used to obtain human data, and 15 layers of cross-sections of young females’ upper body were extracted. In total, 240 space vectors were obtained with the center of the bust cross-section as the original point. By using the principal component analysis and K-means clustering analysis, the body shape classification based on the space vectors length was realized. The garment block corresponding to three body types was obtained using the 3D scanning data and the cross-section convex hull, and compared with existing garment block and evaluated fitness of the blocks.FindingsIn total, 11 main components used to characterize the 3D morphological features of young women were obtained, which could explain 95.28 percent features of young women’s upper body. By cluster analysis, the body shape of women was divided into three categories. The block of three body types was obtained by the construction of the convex hull model.Originality/valueThis paper investigates a classification method of the body shape based on space vector length, which can effectively reflect the difference of surface shape of human body and further improve the matching degree of human body and clothing.