• The Journal of Information Systems
• /
• v.31 no.4
• /
• pp.145-160
• /
• 2022

Purpose The purpose of this study is to develop a virtual try-on deep learning model that can efficiently learn front and back clothes images. It is expected that the application of virtual try-on clothing service in the fashion and textile industry field will be vitalization. Design/methodology/approach The data used in this study used 232,355 clothes and product images. The image data input to the model is divided into 5 categories: original clothing image and wearer image, clothing segmentation, wearer's body Densepose heatmap, wearer's clothing-agnosting. We advanced the HR-VITON model in the way of Mixed-Precison, Gradient Accumulation, and sharing model weights. Findings As a result of this study, we demonstrated that the weight-shared MP-GA HR-VITON model can efficiently learn front and back fashion images. As a result, this proposed model quantitatively improves the quality of the generated image compared to the existing technique, and natural fitting is possible in both front and back images. SSIM was 0.8385 and 0.9204 in CP-VTON and the proposed model, LPIPS 0.2133 and 0.0642, FID 74.5421 and 11.8463, and KID 0.064 and 0.006. Using the deep learning model of this study, it is possible to naturally fit one color clothes, but when there are complex pictures and logos as shown in <Figure 6>, an unnatural pattern occurred in the generated image. If it is advanced based on the transformer, this problem may also be improved.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.45 no.6
• /
• pp.978-985
• /
• 2021

This study aims to propose a prediction model for the drape coefficient using artificial neural networks and to analyze the nonlinear relationship between the drape properties and physical properties of fabrics. The study validates the significance of each factor affecting the fabric drape through multiple linear regression analysis with a sample size of 573. The analysis constructs a model with an adjusted R² of 77.6%. Seven main factors affect the drape coefficient: Grammage, extruded length values for warp and weft (m_warp, m_weft), coefficients of quadratic terms in the tensile-force quadratic graph in the warp, weft, and bias directions (c_warp, c_weft, c_bias), and force required for 1% tension in the warp direction (f_warp). Finally, an artificial neural network was created using seven selected factors. The performance was examined by increasing the number of hidden neurons, and the most suitable number of hidden neurons was found to be 8. The mean squared error was .052, and the correlation coefficient was .863, confirming a satisfactory model. The developed artificial neural network model can be used for engineering and high-quality clothing design. It is expected to provide essential data for clothing appearance, such as the fabric drape.

• Fashion & Textile Research Journal
• /
• v.14 no.2
• /
• pp.261-268
• /
• 2012

The purpose of this study is to investigate problems of design, fitness, suitability for movement, and wearing comfort of jumper for Korean military tank drivers through analysis of actual wearing condition by questionnaire and field evaluation and to provide basic data for developing its improved design. The survey was done for 477 military tank drivers and evaluation was performed using thermal manikin to measure insulation. The overall satisfaction for design of jumper for military tank driver was over 3.5(likert scale). The overall satisfaction for fitness of jumper for military tank driver was also over 3.5. The satisfactions for material was between 2.39 and 3.13 and the satisfaction for pilling property was the lowest, followed by static property and shape stability after laundering. The satisfactions for movement suitability were standing(3.81), sitting(3,38), raising hand(forward: 2.90, sideward: 3.01), respectively. In insulation evaluation of jumper for military tank drivers and outwears(jacket, jumper), the insulation of jumper for military tank drivers was lower than outwear(jumper) and same with outwear(jacket). The insulation in dynamic and still condition(without wind) of jumper for military tank driver was 0.37clo and 0.31clo, respectively. Its decreation rate in dynamic condition comparing to still condition was 59% which was lower than jacket(0.73clo) and jumper(1.15clo).

• Journal of the Korean Society of Clothing and Textiles
• /
• v.39 no.6
• /
• pp.877-884
• /
• 2015

Polytrimethylene Terephthalate (PTT) is an eco-fiber with good elastic properties; however, it requires more detailed studies related to spinnability according to blending of various kinds of fibers. The evolution of spinning technology was focused on improved productivity with good quality; in addition, air vortex spinning was recently invented and applied on the spinning factory as the facility with good productivity and quality. More detail spinning technology according to the blending of various kinds of fibers on the air vortex spinning system is required to obtain good quality yarns for high emotional fabrics. In this paper, the physical properties of air vortex, compact and ring staple yarns using PTT/wool/modal blend fibers were investigated with yarn structure to promote high functional PTT that includes fabrics for high emotional garments. Unevenness of air vortex yarns was higher than those of compact and ring yarns; in addition, imperfections were greater than those of compact and ring yarns, which was attributed to a fascinated vortex yarn structure. Tenacity and breaking strain of air vortex yarns were lower than those of compact and ring yarns, caused by higher unevenness and more imperfections of air vortex yarns compared to compact and ring yarns. Vortex yarns showed the highest initial modulus and ring yarns showed the lowest ones which results in a stiff tactile feeling of air vortex yarns in regards to the initial modulus of yarns. Dry and wet thermal shrinkages of air vortex yarns were lower than ring yarns. Good shape retention of vortex yarns was estimated due to low thermal shrinkage.

• Textile Coloration and Finishing
• /
• v.23 no.1
• /
• pp.35-42
• /
• 2011

For high quality DTP products, it is important to optimize the parameters of media, pre- and after-treatment, ink, printer, etc. This study investigated the effect of types of fabrics(media) as a DTP parameters. Especially, the effects of media properties such as yarn twist and knitted fabric structure, on printability and color difference were examined. Two types of cotton yarn twist(830 and 1630 twist/meter) and five knitted structures of media were prepared with a single circular knitting machine. The K/S values of hard-twist samples were higher than those of normal-twist samples in every media structures. It is more effective to use the knitted fabrics of a hard-twist yarn to obtain dark color in the printing above input level value 60 where the printability improvement was most pronounced in case of plain structure. Among the five media structures a plain structure was the highest and that of corduroy was the lowest in terms of K/S values. Also ${\Delta}E$ values and lightness of the hard-twist yarn samples were smaller than that of normal-twist yarn samples when ${\Delta}E$ values were tested by using a standard of a normal twist yarn sample with a plain structure, which was increased in the case of corduroy structure.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.3_4
• /
• pp.402-411
• /
• 2002

The objective of this study was to investigate sensibility images of Korean traditional motifs cognized by college students in U.S.A. The subjects consisted of 217 male and 351 female undergraduate students. The experimental materials used in this study were 48 stimuli and questionnaires, composed of 7-point semantic differential scales of 15 bipolar adjectives. Twelve motifs selected from 3 groups of Korean motifs were used as motif stimuli. Twelve repeated patterns were constructed from them to be applied on a CAD-simulated dress. The data were analyzed by factor analysis, ANOVA, Duncan's multiple range test. The major finding were as follows: 1. Four dimensions were emerged accounting for the dimensional structure of the images of Korean traditional motifs. These dimensions were ‘quality’, ‘simplicity’, ‘cheerfulnees’, and ‘modernity’. Among them, ‘quality’and ‘simplicity’were the major dimensions. 2. Category, interpretation type, composition type, and application object had significant effects on the images of above-mentioned dimensions. The interpretation type had a significant effect on ‘quality’image, the composition type on ‘cheerful’image, and the application object on ‘modernity’image.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.40 no.6
• /
• pp.1025-1033
• /
• 2016

It is important to compare and analyze digital camouflage from different countries to promote the continuous development of a camouflage combat uniform. This effort should lead to developing a camouflage pattern suitable for the domestic environment and expand its performance of night camouflage. This study investigates digital camouflage by comparing camouflage fabrics sampled from Korea and eight other countries (USA, UK, Singapore, Croatia, Colombia, and Mongolia) in terms of textile, near-infrared reflectivity of colors, and color distribution. First, the fabric construction of camouflage from Korea, UK, US, Singapore, Span, and Croatia were all characterized by derivative plain weaves, while derivative twill weaves were generally used in Croatia and Mongolia. It is assumed that derivative plain weaves are adopted to improve the tearing strength of fine yarns. However, twill weaves enhance the flexibility of coarse yarn fabrics. Next, reflectivity change was analyzed based on camouflage color. The reflectivity of a combat uniform in Korea, Colombia, Croatia, and UK increased before 780nm in the visible light range, but remained consistent from 800nm which falls under the near-infrared range. In contrast, camouflage samples in Mongolia, Span, Singapore and USA showed a gradual increase of reflectivity in the near-infrared range. Finally, the color distribution analysis of digital camouflage found that camouflage of countries with desert or woodland combat settings dominantly contained brown colors. It indicates the color pattern consideration of different geographic regions is important to determine camouflage performance. This research involves basic study that will have implications for developing patterns and colors suitable for the South Korean environment and expand its use as night camouflage that helps achieve continuous improved camouflage performance.

• The Research Journal of the Costume Culture
• /
• v.19 no.6
• /
• pp.1133-1149
• /
• 2011

The major aim of this study was to find out that the relation between consumers value and experience quality toward purchase intention in addition to the influence of the consumers value and experience quality on the effects of scarcity message types collaboration using limited edition in global SPA brand. As a result of an empirical analysis, it shows that consumers value and experience quality are co-related to the intention of purchase, especially, brand familiarity and reputation influenced scarcity valuation in the affirmative and both emotional value and epistemic value influenced the intention of purchase under scarcity message. The moderating effect of consumers value and experience quality however, turns out to be not significant although its effect is directionally supported that is purchase intention was high when scarcity message is shown. Moreover, emotional epistemic group was influenced by scarcity message so we found that consumers value is changed to emotional with subjective. This result indicates that we need the scarcity message type reflecting the characteristics of consumers value and experience quality to increase customer's purchase intention.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.14 no.4
• /
• pp.43-61
• /
• 2012

This research aims to examine the impact of store personality and service quality on the customers' intention of revisiting the department store and their intention of recommendation to others. The participants were women in their 20s to 50s with experiences of purchasing apparel from major department stores. A total of 324 survey responses were used for the final analysis. The data were analyzed using factors analysis, reliability analysis, and multiple regression analysis with PASW 18.0. The results were as follows. First, the department store personality was composed of 3 factors; prestige, passion, sincerity. Service quality factors were defined as tangibility, responsiveness, and empathy. Second, the three dimensions of brand personality-prestige, passion and sincerity turned out to be influential factors affecting the customers' revisiting intention and recommendation intention. Also, tangibility and responsiveness of service quality factors had a significant influence on their revisiting intention, whereas tangibility, responsiveness and empathy factors had a significant influence on their recommendation intention. Third, the sub-dimensions of store personality and service quality had a different influence on the customers' revisiting intention and recommendation intention according to the department store brand.

• International Journal of Costume and Fashion
• /
• v.12 no.2
• /
• pp.1-14
• /
• 2012

To date most of the research concerning e-service quality in the context of online apparel settings has had a female or a generalized for gender and age focus. To expand the scope of understanding of online consumers, this study focuses on the key dimensions of e-service quality which affect male Generation Y consumers' e-satisfaction which in turn may affect their e-loyalty. A convenience sample of male college students was recruited from a Korean university. The findings of this study showed that privacy, personalization, efficiency, and website design were the key dimensions that have significant positive relationships with e-satisfaction. The positive relationship between e-satisfaction and e-loyalty was also confirmed. Managerial implications and suggestions for further research are further discussed.