See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/344765109

Effects of 3D Virtual “Try-On” on Online Sales and Customers’ Purchasing

Experiences

Article in IEEE Access · September 2020

DOI: 10.1109/ACCESS.2020.3023040

CITATIONS READS

17 3,452

4 authors, including:

Hyunwoo Hwangbo Young Jae Jang

Hannam University Korea Advanced Institute of Science and Technology
23 PUBLICATIONS 400 CITATIONS 64 PUBLICATIONS 1,830 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Hyunwoo Hwangbo on 27 October 2020.

The user has requested enhancement of the downloaded file.

 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access

Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier 10.1109/ACCESS.2017.Doi Number

Effects of 3D Virtual “Try-on” on Online Sales

and Customers’ Purchasing Experiences
Hyunwoo Hwangbo1, Eun Hie Kim2, So-Hyun Lee3 and Young Jae Jang4, Member, IEEE
1
Department of Global IT Business, Hannam University, Daejoen, 34430 Korea
2
Big Data Analytics Team, Kolon Benit co. Ltd., Gwacheon-si, Gyeonggi-do, 18337 Korea
3
School of Management, Xi’an Jiaotong University, Xi’an, Shaanxi, China
4
Department of Industrial & Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141 Korea

Corresponding author: Young Jae Jang (e-mail: [email protected]).

ABSTRACT The advancement of the Internet and technology has made it possible to purchase and use
different types of products and services online instead of offline. In particular, as the scale of online shopping
malls is rapidly increasing, new functions have been tried and introduced to compensate for the limitation of
not being able to directly wear clothes in an online mall. Among them, 3D virtual try-on is an innovative
service and its technology is being advanced with continuous interest. Technological advances and interest
in 3D virtual try-on have led to a variety of related studies. Most previous studies on virtual try-on have been
conducted on the virtual fitting technology from the perspective of making clothes, or the effects and customer
behavior from the customer perspective. However, there has been no research based on actual data of
customers using 3D virtual try-on to show how virtual try-on affects sales. Therefore, this study understands
the fundamental meaning of virtual ‘try-on’ as a customer experience and examines the effects of 3D virtual
try-on on online sales. We create a 3D body model complemented by adding more diverse body shapes and
sizes, and investigate the effects of virtual try-on on online sales through actual data. In addition, qualitative
data including interviews are used to complement and interpret the results. The results show that virtual try-
on affects the sales results: the average sales per customer increased by 14,000 won (13USD). The most
important finding is that the return rate decreased by 27% by filtering out incorrect sizes and fits. Virtual try-
on may very well replace physical fitting rooms. This study presents an advanced technology of 3D virtual
try-on and shows that virtual try-on is an effective tool to boost sales and decrease customer’s returns in a
case study of women’s casual L brand.

INDEX TERMS virtual try-on (VTO), 3D clothes digitization, customized body, customer experience,
online sales

I. INTRODUCTION emerged as a compelling retail channel for apparel sales.

During the past decade, interest has grown in three- According to Smallbizgenius (2019), online retail sales grew
dimensional (3D) virtual ‘try-on,’ and has been recognized for 23.3% over 2017 [1]. The online retail sales are expected to
its value as an effective aspect of customer experience. Its account for 13.7% of global retail sales in 2019. Also, the top
original intent was to help customers check out size and fit online purchasing categories in 2018 were fashion at 61% [2].
virtually, but it has become an enjoyable customer experience. To increase online sales, Kolon FnC developed innovative
Since virtual try-on can help customers filter out incorrect projects in previous years to succeed in the competitive omni-
sizes and fits to solve the thorny problem of customers’ channel market environment [3]. Its innovations consist of
inability to wear a garment online, it is very useful in online several information technology projects to attract customers,
malls. In addition, a mix-and-match service can provide establish relationships with customers, and increase online
hedonic value, and 3D virtual try-on has become a significant sales.
feature of online malls. The development of 3D virtual try-on Two critical issues in online sales are the high return rates
has led to hopes that it helps boost online sales, which has and consumers’ hesitancy to purchase apparel. Previous

1
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

research [4] have identified online customers reluctance to relationship between customer experience and real sales
buy apparel because they were not able to wear them to assess results. The purpose of this study is to measure the effects of
the style. In addition, they could easily return a product if it customer’s virtual try-on on the actual sales and to explain the
happens to be the wrong size or fit. Thus, our initiatives have meanings of this customer experience and how it might create
focused on providing relevant, detailed product information value for online customers. Therefore, we developed the
and new experiences with 3D virtual try-on to attract more following research questions:
customers and help them with their decision. Before the
advent of our 3D virtual try-on service, our online customers RQ 1. To what extent is the virtual try-on experience able
only had 2D model pictures and garment size information to to affect sales and consumer behaviors?
make a purchase decision leaving it to their imagination RQ 2. What are the values and meanings of virtual try-on?
weather the apparel will fit. It suits means that the customer
likes the style, and ‘it fits’ means that the garment fits the This study is organized as follows. First, the relevant
customer’s body well. Since online customers are unable to literature about virtual fitting is outlined and the gaps from our
wear a particular garment and do not know whether it looks study and others are explained. Next, the research design is
good, they are reluctant to purchase a garment and tend to explained and the key findings are discussed. Finally, the
return garments for the wrong size and fit. To solve this implications and limits of our research are discussed.
problem, our project concentrates on a 3D virtual model with
a try-on and mix-and-match feature. With this feature, online II. LITERATURE REVIEW
customers can make a virtual model of their own shape and
size and ‘try on’ garments by looking at images of the outfit. A. VIRTUAL TRY-ON(VTO) AT RETAIL/SALES CHAIN
A customer can then decide whether a garment looks good and Virtual try-on (VTO) is a new technology used to help
fits well. In addition, a customer can mix and match garments customers try on and mix and match apparel without a fitting
to coordinate a style. room. In the retail environment, U.S. department stores such
In this study, we use the term virtual try-on (VTO) instead as Macy’s, J.C. Penney, and Nordstrom’s applied new virtual
of virtual fitting because even if a garment shows fit virtually, fitting room technology in the early 2010s to improve their
readers might be confused for the following reasons. In the customers’ retail experiences. It appeared when conventional
fashion supply chain, fit could be checked not only during the shops were in crisis because of consumers’ shift to online
sales/retail process but also at the designing process. First, retailers.[15] VTO technology has been adopted because it has
during the design process, a designer checks the fit to illustrate many advantages in both retail channels. At traditional
his or her design intention aesthetically, and a technical retailers, many consumers feel reluctant to talk about their
designer checks the fit to ensure that the garment fits well on body size and shape with the salesperson, and at online
the body and to fix the patterns to construct well. A pattern retailers, consumers are unable to wear the apparel physically.
professional must then fix the garment patterns according to VTO can then provide consumers with impersonal interaction
the fit guide of the designer and the technical designer. Second, with a virtual model of the customer’s own body that replaces
during the sales/retail process, a customer checks out the fit, the actual try-on, so that it can conveniently provide size and
which helps to make a decision on purchasing apparel. The fit guide. It can solve the problem of incorrect size and fit,
replacement of physical fitting with virtual fitting would save which is a common reason for consumer returns. VTO data are
the costs of making samples in the design process and help significant for retailers because they can explain consumer
customers to buy without having to wear an actual garment. In insights. Because digital simulations can track consumers’
this study, we deal with virtual fitting during the sales process preferences in buying clothes, retailers can use this
and use the term VTO. information to predict sales. In addition, because VTO tends
Most previous studies on virtual fitting or virtual try-on to increase consumer satisfaction, retailers can use this tool to
(VTO) have focused on technology [5, 6, 7], the effects and increase consumer loyalty. Recently, consumers can try
effectiveness [8, 9, 10, 11], and consumer behavior [12, 13, clothes on a model more similar with them by using
14]. These were either studied on its technology in design personalized 3D model using their personal information when
chain from the point of view of making clothes, or studies on they purchase clothes online [16]. In addition, they can check
effects and behavior from the point of view of customers. the wearing sensation not only from the front but also from the
However, no research has been conducted to investigate the back and sides with the use of various angles. Despite these
effect of 3D virtual try-on on sales with actual data. Therefore, advantages, VTO has shortcomings, including poor
this study is to examine how 3D virtual try-on affects the sales simulation of the tactile sense or texture of the fabric. So far,
results. Then, we explain customers’ experience of 3D virtual VTO has been developed with advanced technology including
try-on service by interviewing a group of users of a 3D virtual Microsoft’s Kinect, 3D scanning technology, physical
try-on service. In this study, we explain in detail the advanced simulation with machine learning techniques, GPU-based
information technology of virtual try-on and analyze the real-time cloth simulation, image-based virtual try-on network,
effects of information technology on sales in terms of the multi-pose guided virtual try-on network, and better size

2
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

recommendations [8] [17] [18] [19]. Recent technology has on a model body and seeks a final pattern by iteratively fixing
focused on realistic simulation [20]. Sun et al. (2019) proposed the sample shape. Virtual fitting is the visualization of a
a novel image-based virtual try-on network, which could sample garment to tune in the fits virtually. In a retail
maintain the structural consistency between the generated environment, virtual fitting has become an important aspect of
image and original image by human parsing (see Figure 1) the design process because it can replace some of the samples
[19]. Boonbrahm (2015) [5] researched realistic simulation needed for fitting and can reduce production costs. As an
technology of 3D dress and the physical properties of fabrics example, the U.S manufacturers Target, Kohl’s, and Levi’s
by varying parameters. We can thus tell the kinds of fabrics have adopted 3D simulation technology to check fit in the
used by looking at the appearances of fabric stretching garment sample-making process because of its benefits of
stiffness, bending stiffness, damping, friction, collision, and speed and lower total production costs, and its use is likely to
gravity. This simulation is possible with a 3D game engine, expand in the near future [26]. Retailers understand the weak
Maya, and Microsoft’s Kinect2. points of virtual fitting, which is insufficient to visualize fits
and garment shapes from the perspectives of designers and
technical designers to replace the physical fitting process, but
several U.S. manufacturers plan to use virtual fitting tools in
sample production for cost reasons [6].
In general, virtual fitting technology is similar to
visualization of the garment, yet it differs from VTO in two
ways. First, virtual fitting is usually deployed on apparel
patternmaking CAD systems to assemble 2D patterns of a
garment to drape on a 3D body to shows how it fits on the
body. Several virtual fitting CAD programs have been
FIGURE 1. Image-based virtual try-on network [42] developed by the pattern CAD companies, including Optitex
(Israel), Gerber Scientific (US), Lectra (France), Technoa
VTO technology consists of making a virtual body model (Japan), Assyst (Germany), and CLO Virtual Fashion
from the customer’s own body size, 3D garment modeling, (Korea).[27] Because the purpose of virtual fitting is to tune in
and interactive try-on and mix-and-match of garments.[21] and complete the patterns to reach a quality garment, the
Many studies explain the method of making a virtual body by technology is developed by pattern CAD companies, and the
scanning or measuring the customer’s body. 3D garment 3D geometric rendering is from 2D CAD pattern images.
modeling is done from 2D computer-aided design (CAD) flat Second, virtual fitting requires more advanced technology
patterns or from 2D garment photos. Because the creation of than VTO, because virtual fitting is used to check the fit and
3D garments has been developed using 2D garment photos, fine tune a garment when making a sample. If virtual fitting
VTO can be easily implemented to build a virtual showroom can replace conventional sample fitting during the design
for people who do not have 2D CAD patterns.[22] VTO has process, it would be advantageous to save sample-making
clearly begun to revolutionize the retail scene with advanced time and total production cost [28]. For clothing retailers,
technology such as multiple-sensor 3D scanners, augmented virtual fitting has become a favorite technology for investment.
reality, and simulations. Also, making a good virtual fitting To replace actual fitting, virtual fitting simulation must
room relied on two important factors, the method of detecting illustrate silhouette, detail sizes, fits, ease, realistic fabric
the user’s body size, position, and movement, and the method folds/drapes, and fabric color/texture that looks the same as
of displaying the virtual garments superimposed in the user’s the actual sample [7, 9]. For example, Dongdaemun provides
body [23]. In addition to VTO, social networking features stores sponsored by Seoul with a virtual fitting service of
allow customers to send photos and receive quick producing clothes from virtual clothes designed by customers
feedback.[24] According to the research examining VTO’s using 3D technology within 24 hours. This service is called
results, it helps to boost sales and decrease returns [25]. ‘Within 24.’ Consumers choose basic design samples (design,
Previous studies have concentrated on modeling technology fabric, pattern, etc.) from look books of the 3D cloth
and realistic simulations. They evaluated that VTO technology manufacturing software and try the samples on their avatars to
overall provides adequate visibility to replace physical try-on make real clothes.
and to check the size and fit for customers. However, rather Even though visualization technology is advanced and
less attention has been paid to the effects of VTO in relation overall adequate to represent fits, current virtual fitting is
to retail sales. generally ineffective and cannot replace a designer/technical
designer’s fitting process of the actual sample. Studies have
investigated the similarities of actual garments and virtual 3D
B. VIRTUAL FITTING IN THE DESIGN CHAIN pants, skirts, jackets and other items. One study of pants
Fitting is the process by which designers and technical explained that the waist location, ease, and stress folds of
designers check the garment details, size, and fit of the sample virtual pants differed greatly from actual sample pants.

3
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

Another study concluded that the overall accuracy of virtual interactivity (limited to the mix-and-match feature) and found
fitting was good but insufficient for designers to replace that it acted as a stimulating experience and predicted
physical fitting [6]. Another study evaluated that visualization emotional arousal and pleasure to lead, willingness to
of size variations was enough for viewers to perceive size purchase, and willingness to patronize the online store. It
differences, which means that this size visualization could be means that the use of the mix-and-match feature for
used in the fit analysis of grading samples. As a result, information and for fun is a key to involving emotion and can
manufacturers can replace fit analysis of size grading samples result in a positive attitude in online responses [33]. In addition,
and need not make multiple samples in various size grades or other studies have examined VTO as a marketing feature of
hire multiple fit models of various sizes [10]. However, virtual mobile shopping and the value of mobile shopping and its
fitting is limited and has issues that must be addressed before rapid growth. They attempted to illustrate qualitative analyses
virtual technology can be completely trusted as a visual fit of mobile shopping in terms of convenience and experience
analysis tool. aspects. These studies have explained the main drivers of
Several researchers [11, 29, 30] have evaluated the fit and consumer behavior in a mobile shopping scenario and
style of skirts by comparing similrities between the real fit and illustrated the hedonic and utilitarian value from the use of
the virtual fit. They found that the accuracy of visualization— new features including virtual fitting [13].
for example in terms of shirring, frill, fit point placement, and However, even though many studies have reported on VTO
fabric properties—is insufficient for use by designers and technology and its value, very few studies have reported its
technical designers. In these studies, investigated the fit of effects on actual sales and fundamental meanings of consumer
various items and concluded that it was generally possible to behavior. Therefore, the purpose of this study is to understand
visualize overall fits, but that its limits prevent it from and interpret the qualitative meanings related to the consumer
replacing actual fitting completely. While they recognize the experience with VTO and measure its effects on actual sales.
value of virtual fitting and the new technology of simulation, We define virtual fitting as limited to customers’ try-on at the
they do not think it sufficiently mature to provide precise fits value chain of ‘retailer/sales,’ which is not virtual fitting
to replace sample fitting to fix the patterns. They have during the design process. Our research was performed using
recommended appropriate feedback for better visual the VTO features of L brand, a women’s apparel brand.
representation. This study is limited to VTO, which is a part
of the virtual fitting. III. CREATING VIRTUAL 3D GENERIC BODY MODEL
AND 3D GARMENT DIGITIZATION
C. VIRTUAL TRY-ON AND CONSUMER BEHAVIOR The process of 3D general body modeling, cloth simulation,
Many researchers have studied customers’ attitudes about and customized body modeling is organized as follows (see
virtual fitting features online. Thus far, studies have been Figure 2). First, in ‘1) 3D model creation (human body
confined to analysis of a psychological model, and rather less modeling)’, we created a virtual 3D model by digitizing the
attention has been paid to the effects of VTO on actual sales human body. We analyzed over 1,000 body measurements
results. One study tested the theoretical TAM (technology from our database through 10 line JavaScript code. Here,
acceptance model)[31] and found links among body 34~54 sizes are divided into 11 different sizes through grading.
satisfaction, the VTO experience, attitude toward the product, In addition, the 3D model can be created with 5 somatotypes
and online purchasing intention. The findings were as follows. including the standard body shape and 4 different body shapes
Women with higher body satisfaction tended to perceive more (see Figure 3). The somatotypes include five types, including
enjoyment with the VTO feature. Body satisfaction was not 4 different body shapes and 1 standard body shape. Second, ‘2)
related to the perceived usefulness of the virtual fitting. Both Garment photography’ is a picture of a garment dressed on a
hedonic and utilitarian aspects of virtual fitting play a role in mannequin. It is shot using an automated mannequin handling
determining purchase intention [32]. Another study system. Since the clothes are photographed in mannequins, the
investigated the stimulus-organism-response psychological impression of clothes in real human body can be displayed.
model. It studied the effects of viewing a virtual version of Shooting time is 5-9 minutes per PCS (clothes), saving effort
one’s own body (or ideal body) and body satisfaction on a and time compared to shooting (fitting) a real model offline. It
woman’s concern for garment fit/size and attitude to use VTO. also does not require a professional photographer. Therefore,
The findings are as follows. Women who were exposed to a cost-saving effect is expected.
virtual version of their own body measurements showed Third, in ‘3) Digitization (creation of clothed 3D model)’, we
greater concerns about garment fit and size than those who completed a clothed model through the digitization and
were exposed to an ideal model. It was also found that women rendering of the garment. That is, we performed the work of
who have (1) greater concerns about garment fit and size and cutting out the photographed clothes image and rendering it to
(2) lower body satisfaction are more likely to adopt VTO [12]. the 3D model. These cut outs make the photographed clothes
Another study emphasized the hedonic value of image look more realistic by improving the ability of the rendering
interactivity of a virtual fitting room and its effects on online on the model. These cut outs drive our ability to render 3D
approach responses. It evaluated the effects of image models. The virtual 3D modeling and the cloth simulation of

4
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

this study are a collaborative project with M company, a completed. That is, it is used to create models of outfitted
London-based tech startup that enables VTO online. Finally, images from various angles and to rotate them in try-on. The
in '4) QC (quality control) and realistic effect representation (6 try-on and the mix-and-match services are a part of the online
motions)’, we check out 3D visuals from multiple body shapes mall feature at L brand, a women’s casual brand.
and every angle. And here, a model of six angles was

GARMENTS
BODIES

Garment QC & Realistic

3D model creation Digitization
photography effect representation

FIGURE 2. Process of 3D body modeling, cloth simulation, and customized body modeling

company’s accumulated data. The second step was to build

A. GENERIC BODY MODELING – 5 SOMATOTYPES FOR four more body shapes for each size category because the
11 SIZES standard body type is not applicable to all customers. Our data
To make the VTO fun and interactive, our case study focuses reported that only 22% of our 1.6 million customers could use
on creating an attractive body model, realistic cloth simulation, standard body measurements, so we created four additional
and diverse poses to display the outfit well. We considered body shapes to cater to all other varied body shapes. When we
four major issues. (1) How can we create a customized model defined additional body shapes, we used many specific sets of
with the best quality as we transform the generic body model measurements from the data cluster analysis, and these body
into an individualized body based on a customer’s body characteristics differed significantly from the standard shape.
measurements? How can we reflect varied body shapes and The body shapes are classified as ‘more pear-shaped,’ ‘more
body sizes to cater to all customers? (2) What features make hourglass,’ ‘more rectangular,’ and ‘more inverted triangle’
our virtual model more attractive? How can we generate a [34]. In this study, we generated five groups of body shapes
realistic body and skin tone? (3) When we simulate a garment, based on the customers’ profile, and we defined the ‘standard
can we illustrate the size and fit accurately to help the customer? body shape’ as having similar proportions of the
Can we express the fabric’s physical properties well and circumference of the bust-waist-hip and defined the other four
express the drape and wrinkles so that a customer can feel the somatotypes as follows. As noted, our data indicated that 22%
texture of the clothes? (4) How can we provide interactive and of our 1.6 million customers have a standard body shape, 45%
realistic simulation when a customer tries-on a garment? What are more pear-shaped, 21% have a more hourglass shape, 10%
features make our simulation more fun and more interactive? have a more rectangular shape, and only 2% have a more
Focusing on these four issues, we created 3D generic models inverted triangle shape.
with diverse body shapes and sizes to embrace various
customers’ bodies. We then modified a generic model to an 1) Standard body shape—The bust and hips are basically
individualized body to reflect different body characteristics the same size and similarly proportioned on the
based on the customer’s measurements. circumference of the bust-waist-hip.
The first step in virtual female body modeling was to create 2) More hourglass (rounded)—The bust and hips are larger
a generic female body model from the standard body size than the standard body shape, and the waist is well
measurements. We used more than 1,000 points of body defined.
measurements from our database. Size classification, or size 3) More pear-shaped (triangular)—The hips are large, and
grading, was then conducted mainly on the basis of height the bust is narrow. The hips are fuller than those of the
(stature) and waist circumference (girth). The sizes category is hourglass body silhouette, and the bust is narrower than
divided into 11 sizes from 34 to 54. Basically, the 11 sizes are that of the hourglass silhouette.
identically described as the standard body shape using linear 4) More rectangular (straight)—The bust and hips are
grading. That is, new dataset of body shape is created using narrower or wider than those of the standard body shape.
linear grading as well as the relevant part’s size based on 5) More inverted triangle—The bust is large, and the hips
individuals’ body sizes in order to generate more similar are narrow. The bust is fuller than that of the hourglass
models with each consumer. The data of 11 sizes was created body silhouette, and the hip is narrower than that of the
with the analysis by using machine learning based on the M

5
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

hourglass silhouette. his/her measurements, 3D virtual try-on uses the consumer’s

size and body shape type to create a 3D virtual model. The
The third step was to make our female model more body shape types included the different body shapes in
attractive and realistic using the techniques of animated pose, addition to the standard body shape. The images of standard
color expression, and realistic skin texture. We built various body shape and different body shapes are listed from the left
hair styles, facial tones/expressions, and stylish underwear for side, and the standard body shape of green body curve is also
the virtual model. We tried to represent realistic skin to bring shown on each different body shape image to distinguish
in vividness and built a variety of poses. We tried to present different body shapes by body shape. In other words, an
live skin and build six other poses at every 60° angle rotating individual’s body shape is generated among five body shape
view for being realistic. Figure 3 shows the creation of a 3D groups based on the individual’s own body sizes, based on
model that reflects 11 body sizes and 5 body shapes based on which, 3D model including every angle is developed. Figure
consumer measurements. That is, when a consumer enters 4 shows 3D virtual models with different facial
tones/expressions, hair styles, poses, etc.

FIGURE 3. Process of creating the 3D model with 5 body shapes and 11 sizes

FIGURE 4. 3D virtual models

efficient way. This process begins with 2D garment

B. GARMENT DIGITIZATION AND CLOTHED BODY photographs taken with an automated photo studio system.
MODELING The photographs of garments on mannequins were taken with
Clothed body modeling is used to create a 3D clothed body customized equipment. Since the clothes are photographed in
model by rendering a 3D garment mesh surface on the body. mannequins, the impression of clothes in real human body can
We propose a new method, instead of 2D CAD patterns, we be displayed. Our system does not require a professional
used 3D garment photos; to make a 3D garment mesh surface photographer, and because one coordinator is wearing a
because 2D CAD patterns are always copyrighted and require mannequin costume, it takes only 5 to 9 minutes to photograph
professional CAD software, therefore our study propose an a single piece of clothes, and up to 200 photos can be taken

6
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

each day. It thus saves time and money compared to new nodes are inserted, and some overlapping nodes are
conventional photographing methods. eliminated to make the initial garment surface smooth, and
From the 2D garment photographs, the first step is to Delaunay triangulation is again applied to distribute those
remove the background and extract the garment boundary nodes evenly. This process is iterated, and triangles whose
using image processing techniques such as edge detection and edge is outside the garment region are removed for a good
extraction of feature points. To find a feature point to build a finish.
garment silhouette, each pixel in each column/row is After the garment surface is created, a voxel-like process is
examined to find the first and last background color for each applied to render the planar garment surface mesh onto the
column/row. The garment region is then extracted. Among the virtual body. The garment’s triangulated surface is then placed
candidate feature points outlined here, we used an algorithm near the virtual body, where feature points are used. Between
that selects a feature point of high curvature using a predefined the body and the 3D garment, an efficient collision
feature point mask. We used a supervised learning algorithm detection/response algorithm is used to move the 3D garment
(scaled conjugate gradient) and extended it with new options around the body model. We then sewed eight pieces of surface
[35, 36]. views at every 45 degrees with a feature matching method and
The second step is to reconstruct the garment surface inside used an algorithm to minimize the stitching seam to create a
the garment silhouette. To make its surface smooth and seamless texture. The processing time for 3D garment
balanced, we use an algorithm to insert the interior nodes digitization of each item from the garment mesh is less than 1
uniformly inside the garment silhouette. Delaunay second. Figure 5 represents the digitalization of clothing and
triangulation is applied to produce structured triangles by the process of clothed body modeling.
connecting points to form a convex polygon. In addition, some

Cloth Simulation
System
3D MODELING Clothed Body Model
• Voxel
creation

• Background
removal
GARMENT • Feature points GARMENT
PHOTOGRAPHY detection DIGITIZATION

FIGURE 5. Digitalization of clothing and clothed body modeling

begins. The customer enters five body measurements: height,

IV. CASE STUDY weight, bra size, body shape, and leg length category. If she
wishes a more elaborate body shape, she can enter three more
A. CUSTOMIZED BODY MODEL AND VIRTUAL TRY-ON body measurements: waist girth, hip girth, and inner leg length
Our VTO study was conducted with the online mall and (i.e., from the crotch to the inner ankle bone). She then chooses
mobile application of L brand, a women’s wear brand. The her own model from among 25 faces and hairstyles. With the
most important thing is that the customer enters only five customer’s measurements, the generic model is first modified
measurements, but our customized model reflects the into a customized model.
individual’s body shape and looks attractive with the target The customer can now view a virtual adorned model and
garments. To create attractive individualized models, we rotate it to six viewing angles. Our service recommends the
provided 25 models with various hairstyles and facial right garment size and a fit guide, which includes tighter,
expressions (see Figure 2 and Figure 3). We also focused on comfortable, and looser around the waist and hips. A customer
accurate size and fitting with speed. The process for this VTO also can select other items to mix and match and search for
included four major steps. When a customer enters the main coordinated items. Finally, the customer can share a
page, she selects the ‘try’ icon on the left corner of each photograph of the outfit model via SNS and obtain feedback
fashion style image. The fashion styles are categorized by and opinions from others. This provides the customer with a
brand, type, size, and color to allow the customer to filter new retail experience.
favorable items. The construction of an individual model then

7
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

B. QUALITATIVE INTERVIEWS ABOUT VIRTUAL TRY- congruity’, ‘model styles’, ‘pleasure’, and ‘purchase intention’
ON were mentioned a lot in this order. With regard to ‘model self-
Our VTO service was carried out online in the mobile congruity’, thinking a 3D model created by the virtual try-on
shopping mall of L brand from June 1 to August 13, 2017. A as themselves, they wanted to make the model more similar or
total of 105 SKUs of 2017 S/S styles were presented, and 8058 better than themselves. With regard to ‘model styles’, the
customers used the VTO service. We conducted a telephone contents related to quality or styling of the 3D model were
interview with consumers who used the service to get mentioned, and with respect to pleasure, the use of virtual try-
feedback on the virtual try-on. In addition, we collected ons was found to be interesting. They also said they wanted to
feedback about the service on our website and blog. In the change some parts to become more similar with them in
telephone interview, we encouraged the consumers to talk developing 3D model. That is, they can choose clothes that fit
freely about their experience and feedback about purchasing better if 3D model is developed based not only on body size
clothes using virtual try-on. It took about 15 minutes per but also on the face shape and hair style. Specifically, while
person for an interview. We recorded the interviews and later they were satisfied with the current 3D model, they wanted the
transcribed them. Then the significant phenomena within the face shape similar to them and realistic simulation as if they
data extracted from the interviews were conceptualized and tried on real clothes. Finally, with regard to ‘purchase
coded to categorize similar or related experience. In addition, intention’, it means that consumers are willing to purchase
we web-crawled the reviews on using virtual try-on through clothes through virtual try-on. The actual answers include
the website and blog to use them in the analysis. We used open “The next time I buy clothes,” “I will use virtual try-on to buy
coding to analyze the transcripts. Open coding is the initial clothes” etc.
step of theoretical analysis that pertains to the initial discovery
of categories and their properties [37, 38]. TABLE I
During the open coding, each coder examined the interview CODING RESULTS: CUSTOMER RESPONSES
responses and the comments line by line to identify codes No Customer response Comment examples
1 Confidence in The apparel will fit right, and the size
within the textual data that could explain customers’
apparel fit/style recommendation service is nice.
experience. The coder then discussed each concept identified I am pleased to look at the right length
and named it after arriving at a consensus. We grouped these of pants/skirt.
concepts into broader categories that reflected commonalities I want a more detailed description
about the size/fit.
among the codes. Thus, we used open coding to delineate 2 Model self- The model I used to try-on clothes is
concepts and group them into meaningful categories. To congruity consistent with how I see myself.
validate the data coding results, three other researchers The model looks like me, but if I could
change the avatar, I would like to
reviewed the interview details and keyword classifications. change its proportion for a better look.
We derived concepts from the open coding of the 3 Convenience The try-on service is easy to dress the
qualitative approach about consumers’ virtual try-on 3D model.
It is convenient because I do not have
experience of this study. As a result, we extracted six main to wear clothes many times.
concepts: confidence in apparel fit/style, model self-congruity, 4 Model styles I am satisfied, but I want to view an
convenience, model styles, pleasure, and purchase intention. avatar with my face.
The result of the analysis showed that respondents mentioned I hope it provides the realistic
simulation of cloth.
the most about ‘confidence in apparel fit/style (32.2%).’ Due 5 Pleasure It is fun and awesome
to not being able to see the suitability on online mall it raises 6 Purchase intentions The next time I buy clothes, I will use
concerns for consumers; however, virtual try-on in this study virtual try-on to buy clothes.
recommends size that fits well with 3D models similar to
consumers satisfying their concerns. The actual responses
include “The apparel will fit right, and the size C. EFFECTS OF VIRTUAL TRY-ON ON ACTUAL SALES
recommendation service is nice,” “I am pleased with the look RESULTS
of the right length pants/skirt.” In addition, they said they We analyzed the effects of VTO on actual sales results. To
wanted more detailed description about body size required in measure the effects, we collected customer data and sales data
developing 3D model for virtual try-on. from June 1, 2017 to August 13, 2017. We then cleaned the
Next, they mentioned a lot about ‘convenience’. Consumers data and filtered the return and exchange sales data to extract
were bothered with having to change clothes several times net sales and consolidated the data into one file of customer
when buying clothes. However, they mentioned that virtual net sales data. We analyzed 11,029 transactions, and 8,058
try-on was convenient because they did not have to wear customers used the VTO service. Primarily, we attempted to
clothes. In addition, the use of a virtual try-on system was validate the effects of VTO in the dimensions of time and
found to be convenient. The actual answers include "It's money and compared the sales results of VTO users and VTO
convenient because I don't have to wear clothes many times,” non-users. We measured several indices as follows.
“It's easy to dress the 3D model. In addition, ‘model self-
TABLE II

8
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

INDICES TO ESTIMATE EFFECTS OF VTO Time spent The time stayed online site with the VTO service
is increased by 2.37 time (growth rate of 337%).
Measures Definition Formula Money spent The average sales per customer is increased by
₩14,000 ($13) after the use of the VTO.
Visitor growth Growth rate between the [(visitor count VTO – Sales amount The purchase conversion rate is increased by 2.8
rate average annual visitors average annual visitor times after the use of the VTO.
and visitors during the count) / average annual The return rate is decreased by 27% after the use
VTO service visitor count] * 100 of the VTO.

Revisit growth Growth rate from the [(Revisit count VTO –

rate average annual revisit average annual revisit It is found that visitor numbers, time spent, money spent,
consumer count to count) / average annual and sales amounts increased through VTO in this study. This
consumer count during revisit count] * 100 indicates that consumers revisit the site because they are
the VTO service
satisfied with the virtual try-on service as mentioned in the
Time spent Amount of time a Time spent previous studies that state if consumers are satisfied with a
online customer spent online at service, they revisit the site that provides the service [39] [40].
every visit
The previous studies [41] [42] also view longer stay on online
Time spent Growth rate from the [(Time spent VTO – or offline malls as a positive phenomenon. This means that not
online growth average annual amount average time spent) / only are consumers satisfied with the virtual try-on service, but
rate of time spent to amount average time spent] * also they are interested in making 3D model similar with them,
of time during the VTO 100
service so they use the service while staying longer on the site. Also,
it can be interpreted that they buy clothes easier by actually
Virtual try-on Ratio of the number of (VTO user count / total dressing a 3D model with a body that is similar to their body
participation visitors and try-on users visitor count) * 100
rate
and giving them the same effect as wearing real clothes. The
most key finding is the remarkable 27% decrease in the return
Purchase Rate of conversion, total (VTO items purchase rate, which resonated with other researchers’ opinions. In
conversion resulting number of sales count / items purchase online malls, consumers cannot actually try on and buy clothes,
rate from the number of count) * 100
entities, business that so the return rate is relatively high because they purchase
potentially attracts clothes without actually checking their fit. However, the VTO
purchase in this study allows consumers to dress a 3D model with the
Average A count of items a User : (VTO purchase most similar body to their body through a total of 5
number of customer purchases at item count / VTO user somatotypes including 1 standard body shape and 4 different
purchases per one shopping visit count) body shapes as well as 11 sizes and buy clothes, significantly
customer reducing the return rate. That is, returns due to the wrong
Nonuser : (VTO nonuser size/fit seem to be decreased with VTO.
purchase item count /
VTO nonuser count) V. CONCLUSIONS
This study has three key findings through developing virtual
Average sales Amount of purchase per User : (VTO purchase
per customer a customer amount / VTO user
try-on and examining effects of the VTO on sales results. First,
count) in this study, we created a virtual 3D model reflecting the more
detailed size and type is generated based on the customer
Nonuser : (VTO nonuser measurement, thus making it more realistic and natural
purchase amount / VTO
nonuser count) looking. Second, customers responded positively to this
service. The most significant finding is that the return rate
Return rate the rate of return counts Return count during decreased by 27% through the service. We used the
from the sales counts VTO / Total sales count
consolidated customer net sales data from Lucky Chouette, a
during VTO
line of women’s casual wear from Kolon FnC, from June 1 to
August 13, 2017. A total of 105 SKUs of 2017 S/S styles were
Our analysis illustrates that VTO has positive effects on examined, and 8,058 customers used the VTO service. During
visitor numbers, time spent, money spent, and sales amounts this 2.5 month period, 11,029 transactions took place.
as follows (see Table 3). Third, our observations of customer responses indicated that
they were satisfied with the VTO service with various values.
TABLE Ⅲ The marketing and e-commerce literature consider customer
ANALYSIS RESULTS value to be an important predictor of customer behavior and
Division Results decision-making [43, 44]. Customer value has been used as a
Visitor numbers The revisit rate is increased by 2.24 times after theoretical foundation in explaining customers’ decisions in
the use of the VTO (growth rate of 324%). making purchases [45]. In virtual try-on of this study, when
consumers enter their basic body size, a 3D model similar to

9
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

the consumer is automatically generated, allowing them to https://www.smallbizgenius.net/by-the-numbers/ecommerce-

statistics/.
dress the model with clothes they wish to purchase. This [3] Edaily (2017-09-12). Kolon Fnc, opening of 'omni center'
belongs to a functional value among customer value types. combined with online and offline stores. Available:
Through the VTO, customers could check the size and fit of https://www.edaily.co.kr/news/read?newsId=02318966616059
464&mediaCodeNo=
apparel well, especially pants and skirts. For convenience,
[4] D. Protopsaltou, C. Luible, M. Arevalo, and N. Magnenat-
filtering the wrong size/fit could reduce customer returns, and Thalmann, “A body and garment creation method for an Internet
it was proven to result in a 27% reduction. In terms of hedonic based virtual fitting room,” in Advances in Modelling, Animation
value, consumers feel that it is fun to create a 3D model similar and Rendering: Springer, 2002, pp. 105-122.
[5] P. Boonbrahm, C. Kaewrat, and S. Boonbrahm, “Realistic
to them and dress it, which makes them stay longer at the site. simulation in virtual fitting room using physical properties of
Also, the results show that the average sales per customer fabrics,” Procedia Computer Science, vol. 75, pp. 12-16, 2015.
increased by 14,000 won, or $13. To sum up, VTO could [6] H. K. Song and S. P. Ashdown, “Investigation of the validity of
3-D virtual fitting for pants,” Clothing and Textiles Research
provide convenience, enjoyment, and a new experience that Journal, vol. 33, no. 4, pp. 314-330, 2015.
has a positive effect on purchasing; we conclude that it could [7] O. Sabina, F. Emilia, A. Manuela, M. Alexandra, P. Georgeta,
boost purchase intention and sales in the near future. The most and S. Adrian, “Applied 3D virtual try-on for bodies with
atypical characteristics,” Procedia Engineering, vol. 100, pp.
important contribution of VTO is to replace physical fitting 672-681, 2015.
rooms and help retailers reduce their return rates. [8] E. Shein, “Computing what fits,” Communications of the ACM,
One limitation of this study is that only 8,058 customers used vol. 57, no. 11, pp. 16-19, 2014.
VTO over a period of 2.5 months. In addition, we could not [9] O. Sabina, S. Elena, F. Emilia, and S. Adrian, “Virtual fitting–
innovative technology for customize clothing design,” Procedia
analyze the mass customer responses. Therefore, if more Engineering, vol. 69, pp. 555-564, 2014.
customers’ responses are used over a longer period of time for [10] D.-E. Kim, “Psychophysical testing of garment size variation
more items, the results will reflect more general opinions and using three-dimensional virtual try-on technology,” Textile
Research Journal, vol. 86, no. 4, pp. 365-379, 2016.
elicit better insights with pros and cons about this service. [11] A. Porterfield and T. A. Lamar, “Examining the effectiveness of
However, this study has several implications for researchers virtual fitting with 3D garment simulation,” International
and practitioners. First, this study contributes to our Journal of Fashion Design, Technology and Education, vol. 10,
no, 3, pp. 320-330, 2017.
understanding of the entire relationship of VTO, actual sales, [12] E. Shin and F. Baytar, “Apparel fit and size concerns and
and customer experience and estimates the actual sales effects intentions to use virtual try-on: Impacts of body satisfaction and
via data mining. Second, this study contributes to IS research images of models’ bodies,” Clothing and Textiles Research
Journal, vol. 32, no. 1, pp. 20-33, 2014.
by using customer data to study the effects of a virtual try-on
[13] E. Pantano and C.-V. Priporas, “The effect of mobile retailing on
service on sales results. The previous research lacked consumers’ purchasing experiences: A dynamic perspective,”
examining effects of a virtual try-on on the sales with Computers in Human Behavior, vol. 61, pp. 548-555, 2016.
customers’ actual data. Third, in this research, the VTO [14] M. Beck and D. Crié, “I virtually try it… I want it! Virtual Fitting
Room: A tool to increase on-line and off-line exploratory
service customers were interviewed based on the qualitative behavior, patronage and purchase intentions,” Journal of
research as a way to extract the concepts for using the VTO Retailing and Consumer Services, vol. 40, pp. 279-286, 2018.
service. These extracted concepts were then applied to the [15] A. Kramer. (2011, 2018-06-19). The Virtual Fitting Room.
Available: https://www.strategy-
customer value theory to interpret and explain customers’ business.com/article/00073?gko=790d3
experience. This study also has practical implications for using [16] T. Zhang, L. Cao and W. Y. Wang, " The impact of virtual try-
the VTO services. As the interest in the virtual try-on service on image interaction technology on online shoppers' purchase
decision," In Proceedings of the 8th International Conference on
increases, many fashion companies try the service. This study E-Education, E-Business, E-Management and E-Learning, pp. 6-
can provide guidelines for companies that expand their 10, 2017.
business to the online commerce and companies that plan and [17] H. Dong, X. Liang, X. Shen, B. Wang, H. Lai, J. Zhu,… and J.
operate the virtual try-on service. Due to the tendency of Yin, " Towards multi-pose guided virtual try-on network," In
Proceedings of the IEEE International Conference on Computer
reluctance to face-to-face contact due to COVID-19 along Vision, pp. 9026-9035.
with the development of information technology, the online [18] T. Su, Y. Zhang, Y. Yu and S. Du, " GPU-based real-time cloth
commerce activities of untact services are boosted. According simulation for virtual try-on," In Proceedings of the 26th Pacific
Conference on Computer Graphics and Applications: Posters,
to this tendency and the consumption trend, this study not only Eurographics Association, pp. 1-2.
enhances the convenience and satisfaction level of consumers [19] F. Sun, J. Guo, Z. Su and C. Gao, "). Image-Based Virtual Try-
but also contributes to profit increase of online retailers. on Network with Structural Coherence," In 2019 IEEE
International Conference on Image Processing, pp. 519-523.
[20] P. Volino and N. M. Thalmann, “Implementing fast cloth
REFERENCES simulation with collision response,” in Computer Graphics
International, 2000. Proceedings, 2000, pp. 257-266: IEEE.
[1] Marketing Chart. (2018, 2018-12-07). The too most popular [21] M. Yuan, I. R. Khan, F. Farbiz, S. Yao, A. Niswar, and M.-H.
categories purchased online are…. Available: Foo, “A mixed reality virtual clothes try-on system,” IEEE
https://www.marketingcharts.com/industries/retail-and-e- Transactions on Multimedia, vol. 15, no. 8, pp. 1958-1968, 2013.
commerce-106597 [22] D. Shin and Y. Chen, “3D garment digitisation for virtual
[2] Smallbizgenius (2019, 2019-08-02). 40 eCommerce statistics wardrobe using a commodity depth sensor,” in International
every retailer should know in 2019. Available: Conference on Computer Vision: ICCV 2017, 2017: IEEE.

10
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

[23] C. Kaewrat and P. Boonbrahm, “A survey for a virtual fitting [44] J. C. Sweeney and G. N. Soutar, "Consumer perceived value:
room by a mixed reality technology,” Walailak Journal of The development of a multiple item scale," Journal of Retailing,
Science and Technology, vol. 14, no. 10, pp. 759-767, 2017. vol. 77, no. 2, pp. 203-220, 2001.
[24] C.-I. Cheng, D. S.-M. Liu, C.-H. Tsai, and L.-T. Chen, “A 3D [45] H. W. Kim and S. Gupta, "Investigating Customer Resistance to
virtual show room for online apparel retail shop,” in Proceedings: Change in Transaction Relationship with an I nternet Vendor,"
APSIPA ASC 2009: Asia-Pacific Signal and Information Psychology & Marketing, vol. 29, no. 4, pp. 257-269, 2012.
Processing Association, 2009 Annual Summit and Conference,
2009, pp. 193-199: Asia-Pacific Signal and Information
Hyunwoo Hwangbo received his Ph.D in
Processing Association, 2009 Annual Summit and Conference,
information systems from the Graduate School of
International Organizing Committee.
Information at Yonsei University, Korea in 2017.
[25] I. Pachoulakis and K. Kapetanakis, “Augmented reality
He received his Master’s degree in public
platforms for virtual fitting rooms,” The International Journal of
administration from Yonsei University, Korea in
Multimedia & Its Applications, vol. 4, no. 4, p. 35, 2012.
2008.
[26] K. Salmon, “The coming revolution in retail: Courtesy of 3D
He is an Assistant Professor in the Department
technology,” Kurt Salmon, 2014.
of Global IT Business at Hannam University,
[27] M.-J. Lee and H.-S. Sohn, “A study on the cases of the
Korea. He was an Adjunct Professor in the
application of 3D apparel CAD system to the domestic and
Graduate School of Information at Yonsei
overseas fashion education,” Journal of the Korean Society of
University, Korea since 2019. He was a Senior
Clothing and Textiles, vol. 35, no. 9, pp. 1112-1124, 2011.
Research Fellow of Kolon Benit, co. Ltd., Korea between 2009 and 2018.
[28] C. Morais and G. Montagna, “Customized wardrobe: Clothing
He has published in various journals, including Electronic Commerce
according to user,” Procedia Manufacturing, vol. 3, pp. 5814-
Research and Applications, Expert Systems with Applications, Sensors and
5821, 2015.
the Journal of the Textile Institute. His research interests include data
[29] I. Kang and S.-Y. Lee, “A study on the shape of shirring using
science, Internet of things and big data processing.
3D virtual clothing system,” Journal of the Korean Society of
Clothing and Textiles, vol. 34, no. 7, pp. 1111-1125, 2010.
Eun Hie Kim received her B.S, M.S and Ph.D
[30] M.-R. Koo and M.-A. Suh, “A study on the shape of hem-line of
degrees in clothing and textiles science from Seoul
semi-flare skirts according to a cutting angle-Based on the
National University, Seoul, Korea in 2002, her
comparison between real clothing and 3D virtual clothing,” The
AAS degree in fashion buying and merchandising
Research Journal of the Costume Culture, vol. 17, no. 3, pp. 499-
from FIT, NYC, USA in 1995 and her M.E degree
511, 2009.
in SCM engineering from MIT, Cambridge, USA
[31] F. D. Davis, “Perceived usefulness, perceived ease of use, and
in 2009.
user acceptance of information technology,” MIS quarterly, pp.
She has been a Big Data Analyst with Kolon
319-340, 1989.
Benit in Korea since 2016. Prior to that, she was
[32] U.-J. Yu and M. L. Damhorst, “Body satisfaction as antecedent
SCM deputy manager at LG fashion from 2013 to
to virtual product experience in an online apparel shopping
2016, an SCM consultant at Deloitte from 2012 to
context,” Clothing and Textiles Research Journal, vol. 33, no. 1,
2013, a journalist at Fashionbiz from 2003 to 2008 and a full-time lecturer
pp. 3-18, 2015.
at universities in Korea from 1997 to 2002. Her interests include fashion
[33] A. M. Fiore, H. J. Jin, and J. Kim, “For fun and profit: Hedonic
trend analysis, demand forecasting, S&OP, logistics, product lifecycle
value from image interactivity and responses toward an online
management and AI in the fashion industry.
store,” Psychology & Marketing, vol. 22, no. 8, pp. 669-694,
2005.
So-Hyun Lee is an Associate Professor in the
[34] G. Pisut and L. Jo Connell, “Fit preferences of female consumers
School of Management at Xi'an Jiaotong
in the USA,” Journal of Fashion Marketing and Management:
University, China. Before joining Xi'an Jiaotong
An International Journal, vol. 11, no. 3, pp. 366-379, 2017.
University, she was a Research Professor in the
[35] M. F. Møller, "A scaled conjugate gradient algorithm for fast
Graduate School of Information at Yonsei
supervised learning," Neural Networks, vol. 6, no. 4, pp. 525-
University, Korea. She received her Ph.D degree
533, 1993.
in Information Systems from the Graduate
[36] Y. Chen, D. P. Robertson, and R. Cipolla, A Practical System for
School of Information at Yonsei University,
Modelling Body Shapes from Single View Measurements. In
Korea in 2016. Her research focuses on digital
BMVC (pp. 1-11), 2011.
business, online marketing, and text/data
[37] J. M. Corbin and A. Strauss, "Grounded theory research:
analytics. Her research work has appeared in Information Systems Research,
Procedures, canons, and evaluative criteria," Qualitative
Communications in the ACM, Information & Management, International
sociology, vol. 13, no. 1, pp. 3-21, 1990.
Journal of Information Management, Behaviour & Information Technology,
[38] B. G. Glaser, Basics of grounded theory analysis: Emergence vs
Journal of Database Management, and Internet Research.
forcing, Sociology press, 1992.
[39] S. Campo-Martínez, J. B. Garau-Vadell and M. P. Martínez-Ruiz,
Young Jae Jang received his Ph.D. degree in
"Factors influencing repeat visits to a destination: The influence
mechanical engineering from Massachusetts
of group composition," Tourism Management, vol. 31, no. 6, pp.
Institute of Technology (MIT) in 2007. His current
862-870, 2010.
research includes the "Smart Factory" and
[40] X. Yan, J. Wang and M. Chau, " Customer revisit intention to
"Intelligent Supply Chain and Logistics System."
restaurants: Evidence from online reviews," Information
Hi is cureently the Director of the <Shinsung-
Systems Frontiers, vol. 17, no. 3, pp. 645-657, 2015.
KAIST AI-based Automated Material Handling
[41] C. Astono, " The effect of shopping mall’s attributes toward
System Research Center> leading the multi-
customer satisfaction of ABC mall and XYZ mall," vol. 2, no. 2,
million dollar industry collaborative research
2014.
project with the industry partner, Shinsung FA, Inc,
[42] T. Roux and T. Maree, " Shopper’s Experience of Digital Mall
a global factory automation system provider. He has been also involved in
Signage as Atmospheric Stimuli: An Abstract," In Academy of
the KAIST On-Line Electric Vehicle (OLEV) project to develop and
Marketing Science World Marketing Congress, pp. 321-322,
commercialize the innovative wireless charging electric vehicle. The project
2018.
was recognized as the``50 Best Innovations of 2010'' by TIME Magazine.
[43] J. N. Sheth, B. I. Newman, and B. L. Gross, "Why we buy what
His role in the project is to develop the optimal energy management system
we buy: A theory of consumption values," Journal of Business
to integrate the vehicle system to the road traffic network. He has published
Research, vol. 22, no. 2, pp. 159-170, 1991.

11
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3023040, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2018)

numerous technical papers on OLEV technology. Before he joined KAIST,

he worked at Micron Technology, Inc., VA, USA, where as project manager,
he led a global initiative to improve the efficiency of the manufacturing
facilities located worldwide.

12

View publication stats