• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.434-440
• /
• 2024

SIZE KOREA updates body measurement data every five years, providing essential information for the fashion industry. This anthropometric data is widely used to diagnose consumer body shapes and develop optimal clothing sizes. Artificial intelligence, particularly machine learning, excels in predicting such body shape classifications. This study seeks to enhance the suitability of clothing design by applying the new analytical methodology of machine learning techniques to better capture and classify the unique body shapes of Korean women. In this study, machine learning techniques such as K-means clustering, Silhouette analysis, and Decision Tree analysis were used to classify the lower body shapes of Korean women in their twenties and identify standard body shapes useful for slacks design. The results showed that the lower body of the age group could be classified into three categories: 'small stature' (the majority), 'tall with an average lower body volume,' and 'medium height with a fuller lower body' (the smallest share). The three-cluster approach is validated through Silhouette analysis, which minimizes misclassification. Decision Tree analysis then further defines the criteria for these clusters, highlighting waist height and hip depth as the most significant factors, achieving a classification accuracy of 90.6%. While this study is not directly related to Robotic Process Automation, its detailed analysis of body shapes for slacks patterns can aid RPA in clothing production. Future research should continue integrating machine learning in human body and fashion design studies.

• Journal of Fashion Business
• /
• v.26 no.1
• /
• pp.30-40
• /
• 2022

This study aims to provide basic information on the changes in lower body measurements and shapes of women in their 20s for developing better fitting slacks patterns and a more applicable sizing system that can be widely utilized for women of all ages. Factor and cluster analysis were performed on 1,360 women's direct measurement data within the age group from the 5^th (2004) and 7^th (2015) Korean Human Body Measurement Investigation. The factor analysis identified four factors and explained 82.54% of the total variance; Factor 1, horizontal measurements of lower body; Factor 2, vertical lengths of lower body; Factor 3, measurements of leg and hip areas; Factor 4, lengths of hip and crotch areas. The cluster analysis categorized the lower body shapes of each age group into four shapes; Shape 1, a petite lower body with short legs; Shape 2, a long lower body with medium built; Shape 3, an obese abdomen and legs; Shape 4, a short and slim lower body. Shape 4 (36.5%), Shape 2 (31.2%), Shape 1 (27.8%), and Shape 3 (4.5%) were placed in the order of frequency from the highest to lowest among all the age groups. The findings of this study showed gradual changes in the lower body measurements and shapes of women in their 20s and relevant physical features of each age group. They can be utilized for developing women's slacks patterns with better fitting and more comfort.

• The Korean Journal of Community Living Science
• /
• v.19 no.1
• /
• pp.21-30
• /
• 2008

This study conducted a survey to compare the size of ready-made clothes for different body shapes and body sizes, and to discover the differences in satisfaction with the size of ready-made clothes. The subjects were women in their 208 and 308 from Busan and Gyeongnam. The women were classified into groups: normal weight, overweight, and obese, using the Body Mass Index (BMI). The comparison of the body size showed a significant difference among the shapes; the average BMI in overweight women was 24.2 while that of obese women was 27.6. For the clothing size for each body shape, obese women most often wore size 77 and size 88, regardless of the sizes of upper and lower garments. The size consistency of upper and lower garments was the lowest in obese women. However, in most of the shapes, women tended to choose larger-sizes for lower garments than for upper ones. The more obese the subject, the less inclined they were to wear garments for their real body size. Satisfaction with the clothing size was significantly different between body shapes; the more obese, the lower the level of satisfaction with the size. As well, satisfaction with the fit of clothing at certain parts was shown to be low especially in the bust measurement, shoulder width, upper garment length, crotch length, and thigh circumference. When surveyed about the use of alterations for different body shapes, the results were that over 65% of subjects did not alter upper garments regardless of their body shape. Comparatively, 68% or above of all body shapes did do alterations to lower garments for example, the length of pants or skirts.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.20 no.2
• /
• pp.257-269
• /
• 1996

The puropose of this study was to investigate the movement-fitness according to the surface changing of lower limb The experimental items were divided into the lower limb movements (5) and body-shapes (7). This study was done by the expansion and contraction rate consideration of length, girth Also, the lower half of body shape-change on the movements and body-shapes by flat shell was done simultaneously. The summarized findings resulted from experiments and investigation are suggested as follows; First, when commpared the expansion and contraction rate of the length and girth items, the expansion rate of the back crotch length (14~20%), hip girth (10~ 21%) and knee girth (6.2~18.5%) in rabbit leap movement was the most notable among all variables considered in this experimentation. On the others hand, the front croth length (-22~-52%) contracted remarkably. And big-thigh type was the most notable on the body-shape comparision. Second, in comparision of the expansion and contraction rate of the area on the blocks, the expansion of the hip (50~200%) and knee (51~74%) block was the most remarkable. Especially, in the sit on knees movement of the hip-down type expanded 209.4%. Third, in comparision of the lower half of body shape-change, on the movements and body- shapes by the flat shell, under the influence of knee-joint and hip-joint the shape-changs of the hip and knee block was the most notable. But the shape-change of the waist, abdomen, calf, and ankle was feeble.

• Journal of Fashion Business
• /
• v.11 no.2
• /
• pp.58-75
• /
• 2007

This study held human measurement for 200 male subjects in their twenties in full age living in Ningbo City, Zhejiang Province in China. Their lower body types were classified and grouped according to shapes and sizes. Consequently, representative body type reflecting shapes, sizes, and characteristics were chosen and presented with their measurement values to be used as the basic data for slacks pattern making and fitness evaluation. The following are the results of the analysis: 1. Homogeneity analysis was given to determine the correspondence relationships among index types, indirect types, and size types. Index Type 1 (H-Round), Indirect Type 2 (Adjacent Straight Legs & Slight Slant of Lateral Lower Body), and Size Type 1 (Medium-Thick) were correlated; Index Type 2 (A-Trapezoid), Indirect Type 1 (Bow Legs & Slight Slant of Lateral Lower Body), and Size Type 3 (Small-Slim) were corresponded; Index Type 3 (A-Balance), Indirect Type 3 (Balance Legs & Large Slant of Lateral Lower Body), and Size Type 2 (Tall-Normal) were mutually related. 2. Mahalanobis distance based on each shape factor (index or indirect) and size factor (absolute) was obtained, while an index-absolute representative body type group (47 people, 24.4%) and an indirect-absolute representative body type group (45 people, 23.7%) were chosen, each reflecting shapes, sizes, and characteristics. 3. The representative body type group of lower body shapes of Chinese males in their 20s had average measurement values, such as 169.15cm (stature), 73.32cm (waist circumference), 75.76cm (omphalion waist circumference), 91.08cm (hip circumference), 106.02cm (outside leg length), 53.96cm (thigh circumference), and 74.42cm (crotch length).

• Journal of Fashion Business
• /
• v.10 no.5
• /
• pp.105-121
• /
• 2006

Body measurement was first made with the subjects of 193 males in their 20s residing in the Ningbo area, Zhejiang Province in China. In this first report, lower body shapes were classified and discriminated by using anthropometric measurement indices and lower body analysis. The following sums up the research: 1. Compared with the average values of Korean males in their 20s, the Chinese subjects were characterized with thinner waist, more flat hip, and smaller midthigh. 2. The subjects of Chinese males in their 20s showed three types of lower bodies: H-Round Type (25.91%)-thick waist-abdomen, round cross-section waist-abdomen, and small waist-hip difference. A-Trapezoid Type (34.72%)-small width of omphalion waist-abdomen, average cross-section waist-abdomen, and large waist-hip difference. A-Balance Type (39.38%)-average width of omphalion waist-abdomen, flat cross-section waist-abdomen, and large waist-hip difference. 3. Seven useful variables for the categorization of the subjects' lower body types were chosen through stepwise discriminant analysis, and the hit ratio of discrimination was 96.89%.

• Fashion & Textile Research Journal
• /
• v.18 no.1
• /
• pp.91-102
• /
• 2016

This study classified the lower body types of female adults aged 18 to 69. The lower body was divided into front, lateral front, and lateral back. In order to understand the shape and somatotype of each segment, 592 people were analyzed based on girth, height, length, depth, width, angle and cross section distance for each segment. For data analysis, SPSS 18.0 was performed for descriptive statics, principal component analysis, K-means cluster analysis, ANOVA, and Duncan's test (as verification). Factor analysis was performed based on index values, calculation values, angles, and cross section distances. The measured items resulted in a.) 16 items were extracted to 5 factors in the case of the front factor (FF) of the lower body, and b.) 24 items were extracted to 6 factors in the case of lateral front factor (LFF) and lateral back factor (LBF). Each factor was put through K-means cluster analysis, classifying the lower bodies into one of four types of based on the front type (FT), the lateral front type (LFT), and the lateral back type (LBT) respectively. This study proposed an understanding of various lower body shapes by segmenting and classifying the lower body shapes for each type.

• The Research Journal of the Costume Culture
• /
• v.13 no.1
• /
• pp.6-17
• /
• 2005

The purpose of this research is to define low body shapes of Plus-sized women at ages between 21 and 69 whose satisfied the Plus-sized judgment criteria took part in this study. This research also classifies different body types, and provides basic data for designing skirt's and slacks' prototypes according to each body type. Based on factor analysis of the measured data, seven key factors are grouped. And four different body types are classified based on the cluster analysis using factor marks. Type 1 refers to those who are tall in stature and balanced. This body type is characterized by trapezoid body shape when looked from the front, and slim the abdomen, bulge the belly and flat the buttocks when looked from the side. Type 2 refers to short and an obese body shapes, with trapezoid front and bulge abdomen and belly and flat the buttocks. Type 3 refers to those who are of medium height and long-legged body shapes, with rectangular front, protruding belly and buttocks. Type 4 refers to obese body shapes, with rectangular front, protruding abdomen and belly, flat the buttocks. 9 items are available to judge Plus-sized women's low body types and the hit ratio is 93.5%.

• Fashion & Textile Research Journal
• /
• v.15 no.2
• /
• pp.240-246
• /
• 2013

Data from 540 subjects (included in the obesity group whose BMI was over 25) was selected from 2,445 subjects in the $6^{th}$ Korean Body Size Survey. A total of 25 direct measurements were selected for the relevant literature lower body size measurement analysis, that included 9 components related to BMI, height and circumferences, 3 components related to width and thickness, 5 components related to length, 3 components related to height, and 2 other components. Descriptive statistics, factor analysis, cluster analysis and variance analysis were executed using PASW 18.0 to analyze the data. In accordance with the factor analysis results to classify the lower body shape of overweight women in their 20s to 60s whose BMI was over 25, 4 factors were identified (lower body volume, leg volume, lower body length and leg length). A total of 4 lower body shapes of overweight women were found through cluster analysis using 4 factor scores from the factor analysis. Body Shape 1 had the largest lower body and leg volume. It was the heaviest group. Leg length was at a normal level. Body Shape 1 was 22.2% (122 subjects). Body Shape 2 had the longest legs and the smallest body shape; however, Body Shape 2 was the leg obesity group with the largest leg volume. It was 39.8% (215 subjects). Body Shape 3 had a smaller leg volume in proportion to the lower body thickness and a long lower body length. It comprised 27.8% (150 subjects). Body Shape 4 comprised 9.8% (53 subjects) with the shortest leg. Its lower body obesity was at a normal level.

• Fashion & Textile Research Journal
• /
• v.5 no.3
• /
• pp.235-243
• /
• 2003

This study is to figure out where the current satisfaction with ready-to-wear clothes based on middle-aged women's body shapes is at and to propose basic considerations in its production for coming up with a better sizing system to maximize customer's satisfaction. The data obtained from measurement and questionnaire by 126 middle- aged (35-59) women which were located in Gwangju. Followings are summary of this research, 1)The satisfaction level with lower -wear is relatively lower-wear than that of upper-wear in most parts of body. 2) The results by way of putting score show three different groups. Group 1 has characteristics of front body silhouette in the small ratio of shoulder width/bust width, shoulder width/waist width and big ratio of shoulder width/hip width. And Group 3 has characteristics of front silhouette, small ratio of hip girth/thigh girth. Group 2 has a standard shape. 3) The satisfaction level with lower-wear based on middle-aged women's body shapes shows slight difference. In this category, Group 2 has higher satisfaction level than that of Group 1, while Group 1 has better shape than Group 3. 4) The items of clothes which should be considered current less satisfaction on their size and pattern are skirt and pants. In the meantime, specific body parts for the same criteria are hip girth, thigh girth. And the 43.7% of middle-aged women who responded to this study requires improvement on the fit of lower-wear.