Categorization of lower body shapes for adult females based on multiple view analysis

Abstract

Body shapes are generally identified by subjective comparisons of body silhouettes or by calculating ratios of girths. In this study, we developed a reliable and objective categorization method for the lower body shapes of women using principal component (PC) analysis and cluster analysis. A total of 2,488 women aged 18—35 within the 90th percentile of body mass index (34.14) were selected from SizeUSA body scan data. Body measurements chosen for the analysis include buttocks angle and 14 proportional measures of widths, depths, front/back depths, girths, and front/back arcs of key lower body locations. Five PCs were extracted, but only the first three components made a strong contribution to explained variance (PC1: waist to top hip silhouette, PC2: top hip to full hip silhouette, and PC3: buttocks prominence). However, PC4 (abdomen prominence) and PC5 (slope from abdomen point to front hip point) were also critical for representing a distinctive shape. They had a single variable, and therefore each variable was retained as z-score. Three body shape groups were categorized by K-means cluster analysis using three PC scores and two z-scores. In order to provide a simple and intuitive application method for defining a new person’s body shape group, we developed two discriminant functions using raw measurements. Body shape can be classified within our system from body measurements by calculating function scores and comparing them with a bivariate plot of function scores of the body shape groups.

Data mining and machine learning in textile industry

“…For example, identification of user and usage profiles to innovate, create, and improve textile products and services 10,40 For example, predictive data analysis to understand user requirements in order to be able to design better textile products 46,47,56,57 • Recognition and classification of textile defects for quality control For example, fabric defects 6,8,38,51 (i.e., yarn, woven, knitted, dyeing defects), embroidery defects, 53 and garment defects 50,70 (i.e., cutting, sewing, and accessories defects)…”

“…It helps us better understand the characteristics of data because fewer groups are more easily interpreted. Several studies have focused on the application of the clustering process in the textile industry with the aid of algorithms named K-means, [54][55][56][57][58] Fuzzy C-means, 59 and Hierarchical. 60,61 K-means is an easily implemented algorithm that divides the given dataset into k clusters by determining the centroids of each cluster.…”

“…Garment fitting problems in the textile industry are instances of clustering problems and were tackled via PCA and K-means algorithms 56,57 for size charts with higher fitting. Esfandarani and Shahbari 56 proposed a suit sizing system by segmenting the heterogeneous population to a more homogenous one, and the aggregate loss of fitness is used to evaluate the resultant sizing.…”

“…• Discovering customers' purchasing habits to increase the sales of textile products For example, identification of textile products frequently bought together in order to recommend another item that the customer might be interested in buying as well • Analyzing the records of financial transactions in the textile sector for better decision making 20 • Using DM as a preprocessing step before performing the essential textile study 52 • Text mining to extract interesting patterns and perform textile knowledge extraction from the unstructured textile documents that are obtained from different sources • Clustering the items in textile data to describe the current situation more clearly and to plan different activities for different groups [55][56][57][58][59][60][61][62][63][64][65][66] • Usage of process mining in the context of workflow management and to improve the processes in the textile sector 16,18 Challenges of DMTI Even though DM is a helpful tool based on the above indicated advantages, there are also challenges that could be eliminated. Challenges of DMTI can be classified into four main titles: data preparation, complex nature of textile data, task/algorithms, and postprocessing.…”

Clothing Pattern Construction Systems

“…Oblike krojnih delov morajo biti razvite tako, da uporabniku ponudijo udobje pri nošnji in hkrati omogočijo nemoteno gibanje celega telesa (roke, noge, glava, ramena, pas, boki ...), kar je povezano z ustreznim dimenzijskim prileganjem oblačila meram, oblikam in drži telesa [1][2][3][4][5][6][7][8]. Hkrati ima kroj oblačila pomembno vlogo pri oblikovanju estetske podobe nosilca oblačila [9].…”