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

net/publication/358414870

DEVELOPING GAN'S BASED ETHIOPIAN TRADITIONAL DRESSFASHION

DESIGN IMAGE GENERATION MODEL

Article · February 2022

CITATIONS READS

0 754

2 authors:

Mikiyas Zerfu Tulu Tilahun Hailu

AASTU Addis Ababa Science and Technology University
4 PUBLICATIONS   16 CITATIONS    17 PUBLICATIONS   75 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

artificial intelligence View project

Knowledge Discovery and Data Mining View project

All content following this page was uploaded by Mikiyas Zerfu on 07 February 2022.

The user has requested enhancement of the downloaded file.

 DEVELOPING GAN’S BASED ETHIOPIAN
TRADITIONAL DRESSFASHION DESIGN IMAGE
GENERATION MODEL
Mikiyas Zerfu1,2, Tulu Tilahun Hailu 1,2

Abstract. Technology-driven breakthroughs in the fashion industry, such as artificial intelli-

gence (AI) or machine learning, are revolutionizing every component of this forward-thinking
business area in the twenty-first century. Deep learning, algorithms, and big data have a broad
range of applications in the fashion industry, despite the fast advancement; this paper presents a
comprehensive review on Application of AI in fashion-related works and covering Fashion Im-
age Generation, Fashion Recommendations, Fashion e-commerce and Fashion Virtual tray-on.
The purpose of this research is to explore and assess the use of Generative Adversarial Networks
in the creation of new attractive outfits, as well as to deal with the development of Ethiopian
Habesha fashion clothing images. Three components make up the proposed deep learning model:
(1) Creating a unique fashion image from ready-to-wear Habesha garments. (2) Creating a crea-
tive design picture based on fashion dress patterns and designs (3) finally, using the preceding
two outcomes, image-to-image translation and produce novel fashion dress design. This study,
together with the Framework, explains how to utilize GAN to fulfill the process of fashion design.
Also, offer a mechanism for obtaining and cleaning picture data automatically, as well as a dataset
including over 13,000 images of Ethiopian clothing and over 500 designs and illustrations. Com-
prehensive study has proven that the selected model can be highly useful in the apparel industry.
There is additional information about the lessons learned, as well as a discussion of existing
constraints and potential future possibilities.
Keywords: Generative Adversarial Network, Deep Learning. AI, Fashion Design.

 Mikiyas Zerfu
[email protected]

Tulu Tilahun Hailu

[email protected]

1 Artificial Intelligence and Robotics Center of Excellence, Addis Ababa Science and Technol-
ogy University
2 Department of Software Engineering, College of Electrical and Mechanical Engineering, Addis

Ababa Science and Technology University

2

1 Introduction

Clothing is one of the images and manifestation of human civilization. The clothing
trends and designs represent man's search for beauty from ancient times to the present.
As time progresses, human clothes change in various times, but beauty and creativity
are constantly pursued. Fashion design is an art frame that combines practicality and
creativity. The fashion industry could be a worldwide commerce of 1.3 trillion dollars,
which utilizes more than 300 million individuals around the world [1] and represents a
critical economic drive and a considerable force of global GDP. According to the show-
case analysis provided by a few of the most universal business consultancy companies
(McKinsey, Deloitte Bunch, BCG), fashion companies today are working in a really
dynamic competitive environment, dominated by sudden changes and expanding vul-
nerability. The fashion industry has always been at the forefront of technological im-
provement, whether it is through the sewing machine or the e-commerce market [1].
Innovation during this fashion and attire sector does not solely rely upon product
innovation; however the new digital technologies applied to style and production pro-
cesses are more changing into crucial. Rising technologies features a vital potential to
alter whole production processes and business models for the textile and clothing in-
dustries with an intense work force. Technology-driven developments in the fashion
industry, such as artificial intelligence (AI) or machine learning, are transforming every
area of this forward-thinking business domain in the twenty-first century.
In consideration of the various components of the supply chain which contribute to
the production of industrial materials into products and the delivery of products to the
end customer, the textile and clothing sector is one of the world's largest industries. in
addition to the production and subsequent wholesale and retail of fiber, yarns, textiles,
fashion for men, women and kids, home furnishers and textile soft products, the textile
and clothing industry supply chain comprises. The study of the Fashion industry is
complex and encompasses a wide variety of disciplines including aesthetics, design,
product development, economics, global business, marketing, consumer behavior, op-
erations, and management as well as anthropology, psychology, and sociology.
Today we already continue to see revolutions that would have transformative cul-
tural and social consequences in fields such as AI and Machine learning methods to
artistic activities such as image and music synthesis [2], as well as style transition have
increased in popularity. Artwork is increasingly being created by machines through al-
gorithms with little or no input from humans. AI art has emerged in the later part of the
2010s as a more recent trend in history, drawing on generative and algorithmic ap-
proaches to produce works partially or entirely produced by some kind of machine
learning [3].
AI has a wide variety of applications in the fashion industry through the use of Deep
learning, algorithms, and big data to increase human and market capacities. Such Ap-
plications are design and product creation [4] that help new product creation by analyz-
ing design components such as color, cloth, shapes, and cut. As a designer [5], AI cre-
ates innovative fashion designs along with sewing templates by using a powerful algo-
rithm that analyzes past designs and future trends. AI in textiles can be used in clothing
production by automating cloth quality management, pattern checks, color matching,
 3

and defect identification. From the point of view of purchase and merchandising [6],
AI used in predictive analysis by automatic product labeling and pattern predicting,
personal styling platforms, visual merchandising platforms, and performance measure-
ment. Online product and visual resemblance recommendations complete the look rec-
ommendations, and customized recommendations per country, per user section, and per
individual customer are all examples of AI in e-commerce [7]. AI can be used in auto-
mated product tagging, natural language search, visual search and chat-bot support for
customer care and clienteling, branding strategies, and marketing strategy [6] [8] [9]
[10]. The image generation task becomes simple after the introduction of the generative
adversarial network [11]. There are two types of image generation technology: genera-
tive parametric and adversarial approaches [12]. Several studies have shown that ad-
versarial approaches, particularly the generative adversarial network, have clear ad-
vantages in image generation (GAN).

Contribution of the study

This study survey will have great significance in both academia and industry. The
main beneficiaries of this study can be applied in various domains such as designers
which can be used to easily build designs as a creative method, fashion consumers to
explore new fashion that are not worn before. And This survey serves the researchers,
practitioners, and educators who are interested in creative design and apparel sector
image analysis, with particular emphasis on deep learning-based fashion image gener-
ation.
In addition to these, the key contributions of this survey is described as follows:

 The recent works on DL and image Generation implementations in Fashion design

are discussed explicitly.
 Advise and encourage businesses to use artificial intelligence in their product design
process and serve as a stepping stone for design tool to rapidly produce prototypes
and assist design processes and innovation in the manufacturing industry
 We provide an overview of the state-of-the-art research and summarize their ad-
vantages and limitations. The professionals can easily locate the models for a spe-
cific problem or find the unsolved problems;

2 Literature review

2.1 Overview of deep learning applications for Fashion Industry

AI has a wide variety of applications in the fashion industry through the use of Deep
learning, algorithms, and big data to increase human and market capacities. Such Ap-
plications are design and product creation [4] that help new product creation by analyz-
ing design components such as color, cloth, shapes, and cut. As a designer [5], AI cre-
ates innovative fashion designs along with sewing templates by using a powerful algo-
rithm that analyzes past designs and future trends. AI in textiles can be used in clothing
production by automating cloth quality management, pattern checks, color matching,
and defect identification. From the point of view of purchase and merchandising [6],
4

AI used in predictive analysis by automatic product labeling and pattern predicting,

personal styling platforms, visual merchandising platforms, and performance measure-
ment. Online product and visual resemblance recommendations, complete the look rec-
ommendations, and customized recommendations per country, per user section, and per
individual customer are all examples of AI in e-commerce [7]. AI can be used in auto-
mated product tagging, natural language search, visual search and chat-bot support for
customer care and clienteling, branding strategies, and marketing strategy [6] [8] [9]
[10].
Table 1. Artificial Intelligence Application in Fashion Industry

Technology has always been an important factor for automating fashion, without any
doubt. However, the digital transformation is the spread of digital technology and the
wealth of data created by these technologies. The fashion sector began a more thought-
provoking and quick change, which varies how customers buy and interrelate items and
brands. Fashion & Textiles uses these technologies to better meet their objectives in the
supply chain or employ real-time data and analytics in order to better anticipate demand
and increase prices. In recent decades research into artificial intelligence (AI) and its
implications for the textile and fashion industry has become a much-discussed issue
and gained more attention from academics and industrialists as a consequence of the
unlimiting growth of computer technology [13]. The applicable usage cases have been
widely and severely changed by derived AI and associated technologies. The resultant
efficiency and efficiency of these applications has drawn additional attention and mo-
tivation in other fields, such as: virtual fashion advisors and stylists; market analysis
and predictive analysis; automated client care and chat-bots; and so on.
 5

2.2 Deep Learning Fashion Image Generation

Deep generative technologies have led to the successful production of images/videos,
some to style transmission, and some to a composition of specified conditions [14].
Deep generative models such as the Pixel Recurrent Neural Network (RNN), autoen-
coder (AE), variational AE (VAE), and other forms of Generative Adversarial Net-
works (GAN) have sparked interest in creating or reconstructing samples based on ex-
isting datasets.
The performance of the sewed seam, garment design, other sewing processes and
quality control are being predicted more often by AI. AI may be used for the intelligent
production of clothes in order to forecast the characteristics of clothing following a
certain technique. It may therefore be utilized for appropriate clothing design through
manufacture and monitoring of the processes of production. Based on seam puckering,
seam floating, and seam efficiency, (Hui & Ng, 2009) used ANN to study the perfor-
mance of textiles during garment production. Despite using a little number of training
data, the ANN model proved extremely accurate in detecting fabric defects [15]. In
order to select the best appropriate manufacturing facility for a certain client order, an
AI-based decision support system was utilized in decision making. It can also help with
production planning and control.
Zhu et al. [16]trained a two-stage GAN to create new equipment’s based on textual
description in a given picture, thereby making structural coherence even more con-
sistent with appearance and position. However, its dataset and segmentation maps (128
x 128) constrain resolution since further information is difficult to be obtained. Gu ̈nel
et al [17].'s utilized the conditioning mechanism (FiLM) to combine visual depictions
and textual representations but therefore caused some deterioration without utilizing
any spatial restrictions to meet the same objective In general, the look and pose, form
and texture of the clothes are two categories of fashion components. Some of these
aspects must be disentangled or not altered at the same time, depending on certain ap-
plication circumstances. Li, Y., Yu, X., Han, X., et al.\ 2020 [18]divided the job of
synthesizing garment images into texture and shading, proposing an interactive fashion
image synthesis sketch method. The technology enables users to create contours, pro-
vide various texture information and increase shading by designing shading borders.
To transform this spare information into realistic photographs, deep learning algorithms
are used. A new bi-colored edge representation is suggested to balance output quality
and interaction effort. The study by FashionQ [19] investigates how AI may assist cre-
ativity and identifies key factors to consider when building AI-based creativity support
tools (CST) in the context of ideation in the fashion design sector. Creativity is a sub-
jective notion that varies according to persons and surroundings. In this project, they
worked with fashion designers to learn about their existing design processes, aims, and
difficulties. They built and developed an AI-based CST with fashion designers through
an iterative approach that externalizes three cognitive functions — extending, con-
straining, and blending — in overcoming design fixation throughout the fashion design
ideation process.
One of the main usages from Deep Learning Fashion Image Generation is style trans-
fer. Style transfer converts an input picture to a matching output image for example
6

transfers a real-world image to a cartoon image, or transfers the clothes tested on a

human image, from one style to another. The image processing transfer style includes
a broad variety of applications, such as face make-up and virtual reality [20].

2.3 Deep Learning for Fashion Recommendations

Everyone isn't a natural fashion stylist, the fashion recommendation, given its obvious
applicability for Online Shopping in fashion items, has received ever more attention to
support this requirement. [20].Fashion recommendation works based on Fashion com-
patibility that determines how effectively different types of items can work together to
create attractive attire. Fashion suggestion considers both aesthetic resemblance and
visual compatibility across various clothing kinds.
Convolutional Neural Networks (CNNs) have seen a renaissance as generally effec-
tive image models, notably for personalizatio. Such visual measures were shown to be
useful in interface expectations, for example proposing electing things (for instance two
comparing shirts) or reciprocating things (for instance, a shirt and a pair of coordination
jeans). Chen et al [21]. used a CNN model to create an image-based product recom-
mendation system that included product category identification and similarity calcula-
tions. CNN, a deep learning model, has a lot of potential for developing knowledge-
based apparel recommendation systems because it can not only extract low-level fea-
tures like SIFT and HOG, but it can also train a feature detector to recognize highly
sensitive clothes features and adapt specific classification tasks. As a result, CNNs can
reach greater levels of picture feature extraction accuracy.
When it comes to outfit matching, each outfit usually consists of several complimen-
tary pieces such as shirts, trousers, shoes, and accessories. The matching fashion ele-
ments are crucial to putting together a beautiful ensemble. However, for a variety of
reasons, producing harmonious fashion matching is difficult. First and foremost, fash-
ion is a delicate and subjective notion. Second, there are several qualities that may be
used to describe fashion. This topic has sparked a lot of attention in recent years, re-
sulting in a lengthy number of algorithms and methods.
Al-Halah et al., 2017 [22] are proposing a model that unsupervised manner discovers
fine visual styles from large-scale fashion data. Their approach finds distinct style sig-
natures and describes them semantically based on the main visual features for each one.
In addition, their model also predicts the future acceptance of styles and shows their
life cycle and status based on consumer consumption behavior (e.g. in- or out of fash-
ion). They show that vision, which outperforms textual representations, is crucial to
trustworthy predicts. (Yu et al., 2018) [23] proposes incorporating aesthetic information
into clothing recommender systems, which is extremely relevant to user choice. To do
so, they looked into the use of aesthetic characteristics for customized recommendation
using implicit feedback datasets, then presented the aesthetic features extracted by a
pre-trained neural network, which is a brain-inspired deep structure trained for the aes-
thetic evaluation job. They offer a novel tensor factorization approach to include aes-
thetic characteristics in a customized manner, given that aesthetic preferences vary con-
 7

siderably from user to user and over time. Difficult real-word datasets experiments in-
dicate that the approach offered substantially surpasses state of the art models and suc-
cessfully recommends goods which suit consumer styles.
AI Personal Stylist: Having a personal stylist would be the pinnacle of customiza-
tion, but it would be beyond of reach for the ordinary individual. This is feasible be-
cause to AI, which has enabled the creation of personal virtual AI stylists. This product
represents the confluence of all of the previous technologies: natural language pro-
cessing, natural language comprehension, computer vision, neural networks, and dif-
ferent forms of machine learning. The Virtual Style Assistant is a step ahead, as it high-
lights the use of images, the opportunity to take photos, the ability to recognize images
and search visually as well as the engines for recommendations and accessibility to
fashion goods [24]. Fashion luxury brands in connection with their actual stores use
intelligent mirror technology. Users may utilize the smart mirrors to not only view how
they appear in different colors of clothes, but also to alter clothing types and compare
ensembles side by side. This makes buying much more pleasurable and convenient.
The Beauty e-Experts system was later created by Liu et al. [25] to automatically
propose the most appropriate face haircut and cosmetics, as well as synthesize the visual
effects. It was suggested that the removed facial and clothing properties should also be
used to simultaneously learn multiple super-graphs with tree structure, so as to model
in collaboration the relationships underlying the attributes of beauty (e.g., hair length
and eyelashes color), the beauty of mid-level (e.g. shape of the eye and mouth width)
and the image of low level. In addition, a module to synthesize the qualities of beauty
indicated by the multi-tab structured super-graphs model was also suggested.

2.4 AI for Fashion e-commerce

With the availability of e-commence platforms and the convenience of internet shop-
ping, customers take on a wide range of different alternatives. Purchasing is one of the
most significant activities in our society, and it is vital for the economy and sociology
and psychology to research consumers ’ shopping habits. One of the most popular areas
in e-commerce is undoubtedly clothes. The study of popular and appealing clothing
aspects has been needed, and many developing applications, including clothing recom-
mendations and advertising, might further enhance [26]. Because of the growth of
online purchasing services, the apparel sector is one of today's fastest expanding busi-
nesses. Consumers' frequency in the use of broad0bands and mobile devices, changes
in internet content, future experience in online buying and the continual upgrading of
the purchasing procedure and comfort are among the contributing causes for such huge
development. Online shopping is prominent in apparel among the most popular cate-
gories of e-commerce. The manual observation would be the conventional technique of
detecting the trend of clothes vending and positive design features. However, it takes a
lot of time and will change with the time to time. One major problem of Traditional
Fashion is that the production quantity per design is less compared to the customer’s
demand. Today’s ‘fashion is accompanied by a process of continuous innovation, in
which new designs are developed at sometimes big cost only to be replaced by other
designs. [27].
8

Without AI applications it would be hard to handle the rising scale and complexity
of personalization in digital way. Chat-bots or AI smart assistants are the most popular
solutions for personalized online purchasing. Virtual machines engage with consumers
through chat, reply to customer care requests, assist users to traverse the web and shop
sectors, advise apparel and accessories that suit a particular client as if they were people
who work 24/7 a day. Artificially intelligent chat-bots, on the other hand, can compre-
hend human language and respond to non-predefined inquiries. Customer satisfaction
with live chat is greater (73 percent) than with phone or email, according to studies
[28].

2.5 AI for Fashion Virtual tray-on

Virtual fitting systems bridge one of the greatest gaps between e-commerce and retail.
The goal is an image new fashion picture synthesizing by smoothly merging diverse
elements. These technologies may be used in potential applications from item retrieval
to skilled fashion design helpers. The main objective for VR technology is to generate
a sense of reality that makes it impossible for users to discriminate between actual and
virtual environments. Remote control technology based on robots have drawn increas-
ing attention in society by continuously improving human life and industrial production
requirements. And in many areas, this technology has played a very important role in
the development of relevant research and technical growth.
In the field of display design, it has a very major practical relevance based on the
use of artificial intelligence and VR technology. Clothing is peculiar since it is not uti-
lized alone. The matching of apparel accessories is therefore a significant component
in the process of clothes sales. Good clothes display may be a type of silent education,
not simply for buyers. Customers don't have to display a bad attitude so that they may
learn how to match apparel. The exhibition shows the beauty of its clients directly and
transmits the artist's ideas through this neutral medium. There's no anybody in the
crowd any more. If you don't have self-emotions, like envy, you will more likely em-
brace a concept. When the buyer accepts the notion, he agrees, of course, that the prod-
uct is actually lovely and simpler to purchase [29]. The aim of display is to present to
our customers all the material and emotional characteristics of goods and brands using
creative methods and design techniques as well as other visualized languages.
In luring consumers into the retail shop or visiting a website, visual merchandising
has a vital role. In the store and on the Internet, visual merchandise is increasingly uti-
lized to improve consumers' buying experience and to extend the accessibility of the
brands. Visual merchandising displays are very influential for customer shopping. The
manner that goods are marketed and presented in the shop may have a significant effect
on the behavior of consumers. According to the findings of several studies, visual mer-
chandising of intimate clothing has a modest influence on female customer purchase
behavior, since the majority of female consumers dislike the usage of mannequins for
lingerie display. e-commerce provides a judgement-free environment in which to ac-
quire the goods, as well as a wider range of lingerie products in terms of design and
color [30].
 9

The acquisition is visual. Looking at is what is purchased. Brands have acknowl-

edged this worth and promote themselves to draw the interest of the customers. Dis-
plays must only appeal in visual terms, to engage and motivate the client. Consumer
behavior is also visual and tactile and senses are used for purchase. The desire to see,
touch and when everything is pleasant to the impacts of a purchase have maintained
marketers and retail experts investing in visual professionals, engaging more custom-
ers. Visual merchandising facilitates the location and self-selection of a product for a
consumer. Some displays show the customer how to wear a product in the event of
clothing and how to utilize a product. It is also the technique to move the items of slow
sales – to make them enviable for the consumer and they choose it off the shelf or from
the web shop [31].
AI will certainly drive the fashion industry to a more sustainable environment, ex-
pand business models for retailers, and make them more affordable. AI is also expected
to radically disrupt the fashion industry, not only because of new business models and
production processes, but also because the individuals who work in the fashion industry
and their vocations will undoubtedly have an influence. Artificial Intelligence (AI) is
sometimes considered as less serious. Important fashion figures. AI has the potential to
progress in many sectors of the value chain, and others will follow. We can use AI for
selection with a lot more data science. This might extend all the way to the back-end
infrastructure and production. It does not entail the greatest product range; it concerns
providing customers with the most apparent diversity.
A lot of study has been done to create virtual model 3D clothing. Some employ
unique multi-camera configurations to record 4D changing clothing form [32]. Other
techniques are used as input for 2D sewing patterns [33] or 2D sketches, which are easy
to produce 3D input models. Another set of 3D template molding technology designs
textile clothing that fits finest 3D human virtual models [34]. Image-based virtual try-
on has also been considered as an alternative to 3D modeling. Neverova et al. have been
using the two-stream network, combining a predicted image driven by data and a tan-
gled surface picture, while at the same time learning from one end to the other to pro-
duce a new personal position [35].
When we think of AI for Virtual Tray on we also need to investigate Semantic seg-
mentation. Every pixel is allocated with semantic annotations Semantic segmentation.
CNNs were used for this assignment successfully. For semantic segmentation Long et
al. introduced Fully Convolutional Networks (FCNs), which resulted in major advance-
ments on handmade techniques [36]. Built on FCNs, the architectures of the encoder-
decoder were a fantastic results [37].
Given a source picture and a 2D-target position, image-based techniques create an
image at the target position with the source appearance. It is useful to change the pixels
into an original picture to match the target posture within the network in order to cope
with pixel misalignments. Similar principles of developing GANs may be used to pro-
duce high-resolution anime characters [38]. Synthesis of try-on and conditional clothes.
There are an increasing number of recent papers on making the picture creation condi-
tioned on a specific piece of clothing or a description. Additional works have shown
models that can exchange appearances among two separate subjects [39] [16].
 10

2.6 Related works

Table 2. Related works summary

Paper. Methodology. Objectives. Research Limitations.

The model does not gener-
Automatically gen-
An image synthesis pipeline ate new Fashion design im-
erated fashion im-
that can generate garment im- age but simply implement
age and establishes
Fashion GAN ages based on a fashion sketch virtual garment display.
a bijection relation-
and a specified fabric image us- And workable only for sin-
ship between gener-
ing CGAN to show image gle-color and regular fabric
ated images.
pattern
To present a novel Not considering using De-
Given a person's input image
Be Your Own and effective ap- sign sketches. Moreover,
and a text, that describes a de-
Prada: Fashion proach for generat- training set contains images
sired outfit, And then the model
Synthesis with ing new clothing on mostly with a plain back-
output the person with a new
Structural Coher- a wearer through ground.
dress, while maintaining the
ence generative adversar-
wearer's and pose unaltered.
ial learning.
Garment Design Attribute GAN (AttGAN) To automatically Lower resolution and qual-
with Generative which is a generative model edit garment images ity of the generated image.
Adversarial Net- proven successful for attribute based on certain And It does not consider
works editing of human faces is uti- user-defined attrib- many conditionals except
lized for automated editing of utes. shape and color.
the visual attributes of gar-
ments.
GAN-based visual- By using ProGan and as input it To design and de- Not Considering the main
aware interactive takes the masks of the images velop an interactive Conditionals like Pattern,
fashion design and adding the conditionals into fashion design Shape, texture and not huge
framework the masks. framework set of colors. And The gen-
erated image has low qual-
ity and the model outputs
inconsistent results.
TailorGAN: Mak- By using two methods those are To investigate the Not Considering the De-
ing User-Defined reconstruction learning step problem of doing sign sketching process from
Fashion Designs which the model learns texture image editing to a scratch rather than it manip-
and location information and fashion item with ulates from the garment im-
adversarial learning step which user defined attrib- age. and Does not contain di-
has the capability to achieve ute. And To gener- versity in their datasets.
single-attribute manipulation. ate photo realistic
images with desired
attribute.
 11

3 Data and Method

3.1 Concept Development

The work process started with a fairly broad scope to become acquainted with the area
of deep learning. When adequate information had been acquired, through reading vari-
ous papers and study results, the scope was limited to concentrate on the most relevant
topics. Since artificial intelligence and deep learning are fields of study yet to achieve
stability, new results are published regularly and it is impossible to intuitively, develop
a judgment on what network topologies are most suited for particular tasks without first
having a broader perspective.
Fig. 1. Concept development process

3.2 Dataset Preparation and Preprocessing

The suggested architecture objectively should be by utilizing a fresh custom dataset.
This is intended to be done by gathering Ethiopian traditional dress fashion products
images and fashion design sketch images. This custom Dataset collected from the fol-
lowing sources:

a. Ethiopian Fashion Design School: This method of collection dataset is a collec-

tion of 500+ images with different sizes. The images are of design sketches from
different fashion design school and universities.
b. Web Scrapping: An automatic gathering system utilized to simplify the process.
To automate the process of collecting training data this study present a system,
based around a web scraper and an object identification model.
c. Custom Capturing: Taking a picture of the wearable fashion product from differ-
ent stores around Addis Ababa.

Pre-processing Techniques.
After gathering the required data, the following stage is conducting pre-processing
on the obtained face pictures to eliminate some distortion, resizing, and filling the con-
tent to make them with same dimension using various methods. Clean background is
important to display the core portion of desired product in the picture. Due to this, all
training pictures had the clean background. For removing background of images this
research utilizes different API’s that are suitable for this purpose. E.g. clapcut, re-
movebg ... etc.
12

3.3 Hardware and Software tools

Investigation of available software tools with their libraries are conducted in order to
select the appropriate tool for the implementation. Software tools that have used to im-
plement the algorithm are python as a programing language with TensorFlow libraries.
These tools fulfill all the consideration criteria’s and they are used in python which is
familiar to us. We implemented our algorithms and networks on Google Colab Pro+
since GPU is required and GAN will not train effectively only with a CPU.

4 Design and Experiment

4.1 Proposed model architecture

This study’s choices of model from various machines learning aspects is Generative
Adversarial Networks that can create fake image but look realistic images with the uti-
lizing of two neural networks namely “Generator” and “Discriminator” in which they
act against one another, that's why the model have the name "adversarial." Both neural
networks have specific roles. One is a convolution neural network that plays the role of
a discriminator/classifier of the generated images whether they are real or fake, and the
other a reverse convolution neural network that plays the role of a generator which is
responsible for generating fake images.
Finally, this study will train a new GAN (Generative Adversarial Network) model
by combining different generative adversarial networks model to generate a novel fash-
ion image with the best quality, good aesthetics and beauty, also based on different
user’s fashion design conditionals. Then the model will be evaluated for validation pur-
pose.

Fig. 2. Proposed model architecture

Two Main different Generation Model are conducted during the experiment to test the
proposed idea. The first one is StyleGAN. The Second one is StyleGAN2AdaIn. Sev-
eral experiments are conducted on the proposed model by changing the ratio of training
dataset, with different test networks.
 13

4.2 Experimental Setup and Implementation

The primary task is to ensure that each image in the data collection has the same format
in terms of dimension, extension, and background. Any irregular images will be auto-
matically transformed to the required image and saved to the dataset. The training is
done on Google Colab Pro since GPU is required and GAN will not train effectively
only with a CPU. We must mount the dataset from the disk to the cloud. The training
needs square pictures, and images with a size of 1024 x 1024 are required for extremely
high quality. However, this study used a resolution of 512*512, and the next step will
be to resize all of the pictures to this resolution and use PIL, which is a Python library
to transform an RGBA image to an RGB image. After opening a picture, use Im-
age.new(mode, size, color) to generate a new RGB image with mode set to "RGB", size
set to the desired image size, and color set to (255, 255, 255). Using Image.split and
Image.paste (picture, box, and mask) with image as the original image and mask the
alpha channel. Image.split () extracts a tuple of separate image bands from an image
(red, green, blue, alpha). Index into three to obtain the alpha channel. Then call Im-
age.save (filename, format, quality) to save the improved image with the filename as
the filename, the format override format, and the new image's quality.
Once the custom dataset has been transferred to Colab and resized, by using the fol-
lowing commands to convert the custom images to tfrecords. Now go to our training
folder and open the train.py file with our generated tfrecords custom HabeshaDressSet.
And then we set the number of GPU’s. since this research is conducted on Colab pro
plus it only allows 1 GPU, therefore we set our training with this GPU. Then this study
use the number of epochs to 12000 because of the longest time that Colab can allow us
and it is efficient for our resolution type. Training will stop after this much iterations.
Then we set the inception pkl file form StyleGAN since it shows effective result in
generation of quality celebrity faces and different datasets.
Also, this research uses transfer learning for inception features from StyleGAN.
Therefore the inception_v3_features.pkl file from StyleGAN GitHub to our training
folders. And insert in our Fréchet distance file.
We are now all set to go for training our own Model. After the training Once, our
training is over, there will a directory created that contain results of the training which
include a lot of network-snapshot pickle files created. we need to get the latest .pkl file
and use the weights of that file.

5 Results

After successfully training the GAN model, it is now able to generate new samples that
look similar to the training dataset. In this section, the experimental results of the model
are shown to understand the usefulness of the trained generator in fashion design pro-
cess. Two tests have been conducted in the identical hardware and software, hyperpa-
rameters, and dataset setup. each experiment suggested insights by employing transfer
learning and introducing an additional condition style based generative adversarial net-
work.
14

5.1 Scenario 1: Changing Training and Testing Dataset Ratio

Fig. 3.

5.2 Scenario 2: Changing Learning Rate

Fig. 4.

5.3 Failure Examples

 15

6 Discussion

In this research, we have studied how ai systems, especially in the area of deep learn-
ing, might be implemented into the design management process to make processes cre-
ative, quicker, easier or more effective. The intention was that this study would lead to
broad recommendations and enable us to construct a framework to motivate, support
and guide organizations and designers interested in taking a first step in applying arti-
ficial intelligence to generate innovative designs.
The work process started with a fairly broad scope to become acquainted with the
subject of deep learning. When adequate information had been gathered, through read-
ing various papers and study results, the scope was reduced to concentrate on my pas-
sion and Fashion industry. The implementation stage of presented concept was employ-
ing transfer learning using StyleGAN with TensorFlow to create and train neural net-
works in Python. The decision of utilizing these Model and libraries over others was
determined early based on primarily it is applicability for this research and acceptance,
community sizes and for being open source. They are also extremely well documented
with various examples and tutorials, which have been a helpful resource along the road.
When it comes to the custom dataset, the model had some challenges to create syn-
thetic pictures equal to the real data. Several explanations are behind the issues. First,
several images inside the collection contain some noise in terms of other things besides
Habesha garment, are included in the images. If the dataset is inspected, one may dis-
cover things such as a two dress in one picture, logo and trademarks, store location,
Traditional materials and many other objects. Moreover, some photos have one dress
while others might contain numerous outfits. All these characteristics make it harder
for the Model to gather the features of the classic dresses and designs. Secondly, the
size of the dataset also plays a factor. For the habesha dresses images dataset there are
more than 10000 samples. The final argument concerns the capacity of the StyleGAN
assuming that it is not already adequate. The model may require some further fine-
tuning in order to become better however due to lack of time the researcher did not go
on with it. Comparing the findings from the two different sizes employed, training a
model on bigger photographs proved to boost the visual quality of the images. One
explanation might be because details are overlooked in images of reduced size.
A challenging problem that affects the outcomes from an experiment is that they
must be both reliable and accurate. Reliability refers to the repetition of results that is
when a phenomenon is tested repeatedly, the conclusion must be relatively comparable.
Additionally, objective metrics are more accurate than subjective assessments. The re-
searcher assure that the findings from the experiments are reliable because every ex-
periment was done at least triple, and every time an experiment was run extremely
comparable outcomes in quality and variation were produced. Anyone who conducts
the tests that have been done in this paper using the same technology (hardware and
software), datasets and setups with identical period, which is 72 hours, should achieve
comparable conclusion.
Since this thesis attempts to encourage and motivate the usage of artificial intelli-
gence it is important addressing the probable long-term repercussions. The automation
enabled by artificial intelligence, driven by deep learning, might certainly lead to the
16

termination of some conventional occupations. This is something that goes hand in

hand with technology improvements. Since the implications of artificial intelligence on
diverse professions is unpredictable, the transition needs a high degree of flexibility and
preparedness for multiple result scenarios in order to be seamless.

7 Conclusion and Recommendations

The major purpose of this study is to look at how generative adversarial networks
(GAN) may be used to allow automated fashion picture production and how such tech-
nologies might help professional fashion designers with their creative designs.
As a result of the current advancement of GANs in the fashion sector, we were able to
generate some new fashion images with improved quality, create virtual cloth genera-
tion consisting of new designs and patterns, study the distribution of fashion images,
and develop new clothing and accessories that maximize users' interests. GAN may be
used in a variety of Fashion suggestion scenarios, such as discovering the world of new
fashion goods, changing existing items, or developing items tailored to a person and
assisting in the creation of new products. Another key item to note is that, like with
practically every ML technique, data pretreatment is critical for training GAN's model
performance. The findings clearly showed that the chosen could readily create high
quality samples of other datasets; however, the bespoke Habesha clothing dataset im-
ages had issues because the dataset was not well preprocessed and had some noise.
COVID-19 pandemic still is a significant worldwide health threat. Most African
In the future, this opens up a potential line of study in applying GAN’s architecture
for Generating and recommending fashion design. The next work need to investigate
boosting the quality and resolution of the produced pictures and giving control of fine-
grained styles, the same principles may be extended other visual data besides fashion
photographs, or even to non-visual forms of material. Evaluation of GAN’s perfor-
mance and preserve the realism of human postures and faces will also be an essential
subject to research.
The present approach creates unique and believable naturally pictures in a random
way. A logical issue is if we can enhance this automated design, process to be goal-
oriented like human designers would do. For example, the design outcomes may be
repeatedly developed according to specific criteria, where methods such as reinforce-
ment learning can be utilized. However, this needs excellent quantitative measures on
originality and utility of the created products, which remains a tough unresolved topic.
Evaluation of the produced results technique are likewise an open research topic.

Funding: This research received no external funding.

Conflicts of Interest: The authors declare no conflict of interest.
 17

References

[1] Imran Amed, Anita Balchandani, Jakob Ekeløf Jensen, Achim Berg, Felix
Rölkens, "The State of Fashion 2021," McKinsey and Company, 2021.
[2] Christie's, "Is artificial intelligence set to become art’s next medium,"
Christie's, 12 12 2018. [Online]. Available:
https://www.christies.com/features/A-collaboration-between-two-artists-one-
human-one-a-machine-9332-1.aspx. [Accessed 24 march 2021].
[3] D. Flaherty, "Artistic approaches to machine learning," vol. 1, p. 13, 2020.
[4] "AI in Fashion: An Extensive Guide To All Applications For Retail,"
Intelistyle, 03 December 2020. [Online]. Available:
https://www.intelistyle.com/ai-fashion-retail-applications/. [Accessed 04
April 2021].
[5] M. S. Kim, "AI as a Designer?," Medium, 08 August 2020. [Online].
Available: https://medium.com/sfc-interaction-design-class-2020-spring/ai-
as-a-designer-3fce8db9451e. [Accessed 04 April 2021].
[6] "Artificial intelligence in the fashion industry," Research Features, 04
March 2021. [Online]. Available: https://researchfeatures.com/artificial-
intelligence-in-fashion-industry/. [Accessed 04 April 2021].
[7] "How to Use Artificial Intelligence (Ai) in Online Fashion Retail in 2021,"
Exponea, 12 January 2021. [Online]. Available:
https://exponea.com/blog/impact-artificial-intelligence-online-fashion-retail/.
[Accessed 04 April 2021].
[8] Marie Korneliusson, John Martinsson, Olof Mogren, "Generative
Modelling of Semantic Segmentation Data in the Fashion Domain," 2019
IEEE/CVF International Conference on Computer Vision Workshop
(ICCVW), 2019.
[9] Othman Sbai, Mohamed Elhoseiny, Antoine Bordes, Yann LeCun, Camille
Couprie, "DesIGN: Design Inspiration from Generative Networks," Lecture
Notes in Computer Science, pp. 37-44, 2019.
[10] Katrien Laenen, Susana Zoghbi, Marie-Francine Moens, "Web Search of
Fashion Items with Multimodal Querying," Proceedings of the Eleventh ACM
International Conference on Web Search and Data Mining, vol. 1, 02-2018.
[11] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David
Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio,
"Generative adversarial nets.," In Proceedings of the 27th International
Conference on Neural Information Processing Systems, vol. 2, 2014.
[12] Donggeun Yoo, Namil Kim, Sunggyun Park, Anthony S. Paek, In So
Kweon, "Pixel-Level Domain Transfer," European Conf. on Computer Vision,
2016.
18

[13] S. Bagai, "Artificial Intelligence: Automating the Fashion & Textiles

Industry," in Fashion & Textile Industry 4.0 - Opportunities & Challenges for
Education 4.0, India, 2021.
[14] Lele Chen,Justin Tian, Guo Li, Cheng-Haw Wu, Erh-Kan King, Kuan-Ting
Chen, Shao-Hang Hsieh, Chenliang Xu, "Tailorgan: Making user-defined
fashion designs," 2020 IEEE Winter Conference on Applications of Computer
Vision (WACV), 2020.
[15] C. L. H. a. S. F. Ng, "Predicting seam performance of commercial woven
fabrics using multiple logarithm regression and artificial neural networks,"
Textile Research Journal 79, vol. 18, 2009.
[16] Shizhan Zhu, Sanja Fidler, Raquel Urtasun, "Be Your Own Prada: Fashion
Synthesis with Structural Coherence," in Proceedings of the IEEE
International Conferenceon Computer Vision, 2017.
[17] L. Liu, H. Zhang, Y. Ji, and Q. M. Jonathan Wu, "Toward AI fashion
design: An Attribute-GAN model for clothing match,," Neurocomputing,, vol.
341, pp. 156-167, 2019.
[18] Y. L. a. X. Y. a. X. H. a. N. J. a. K. J. a. J. Lu, "A deep learning based
interactive sketching system for fashion images design," 2020.
[19] Y. &. S. P. &. H. K. &. J. S. Jeon, "FashionQ: An AI-Driven Creativity
Support Tool for Facilitating Ideation in Fashion Design," pp. 4-10, 2021.
[20] S. S. C.-Y. C. S. C. H. J. L. Wen-Huang Cheng, "Fashion Meets Computer
Vision: A Survey," ACM Computing Surveys, vol. 54, no. 4, pp. 1-41, 2021.
[21] Hao Dong, Simiao Yu, Chao Wu, and Yike Guo, "Semantic image
synthesis via adversarial learning Computer Vision.," in IEEE International
Conference on, 2017.
[22] Al-Halah, Z., Stiefelhagen, R., & Grauman, K., "Fashion forward:
Forecasting visual style in fashion," 2017 IEEE International Conference on
Computer Vision (ICCV).
[23] Wenhui Yu, Huidi Zhang, Xiangnan He, Xu Chen, Li Xiong, and Zheng
Qin, "Aesthetic-based clothing recommendation," in Proceedings of the 2018
World Wide Web Conference on World Wide Web - WWW '18, 2018.
[24] P. F. Masciarelli, "Artificial Intelligence and the Fashion Industry," LUISS
Department of Economics and Finance, 2018/2019.
[25] J. X. S. L. H. X. X. Z. S. Y. Luoqi Liu, "Wow! You Are So Beautiful
Today!," ACM Transactions on Multimedia Computing, Communications, and
Applications, vol. 11, no. 1s, pp. 1-22, 2014.
[26] Kuan-Ting Chen, Jiebo Luo, "When fashion meets big data," Proceedings
of the 26th International Conference on World Wide Web Companion - WWW
'17 Companion, 2017.
[27] Jashim Uddin Ahmed,Md. Humayun Kabir, asim Uddin, "Sadakalo:
Marketing of Traditional Fashion in the Modern Fashion Industry," June 2014.
 19

[28] C. Joy, "Evolution of Commerce: How AI is disrupting the Fashion

industry," UNBXD, Dec. 2017. [Online]. Available:
http://unbxd.com/blog/ai-‐fashion-‐industry. [Accessed 14 September 2021].
[29] Lai, HuiJuan, Lee, SungWon, "The Application of Artificial Intelligence
and VR Technology in Clothing Store Display Design," vol. PP, 2020/08/31.
[30] S. Verma, "Effect of Visual Merchandising Display on Consumer Buying
Behavior towards Intimate Apparel," in Proceedings of online National
Conference on Fashion Apparel and Textile (NCFAT’20), Swami Vivekanand
Subharti University Meerut India, 2020.
[31] S. Fernandes, "Influence of Visual Merchandising on the Consumer," in
Proceedings of online National Conference on Fashion Apparel and Textile
(NCFAT’20)Fashion & Textile Industry 4.0 -, India, 2020.
[32] D. Bradley, T. Popa, A. Sheffer, W. Heidrich, and T. Boubekeur,
"Markerless garment capture.," ACM Trans., p. 99:1–99, Aug.2008..
[33] A. G. D. M. K. E. G. a. M. A. F. Berthouzoz, "Parsing sewing patterns into
3d garments.," ACM Trans., July 2013. .
[34] C. C. L. W. a. X. J. Y. Meng, "Flexible shape control for automatic resizing
of apparel products.," Comput. Aided Des., p. 68–76, Jan. 2012..
[35] R. A. G. a. I. K. N. Neverova, "Dense pose transfer," in In The European
Conference on Computer Vision (ECCV), September 2018.
[36] E. S. a. T. D. J. Long, "Fully convolutional networks for semantic
segmentation," in In 2015 IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), June 2015.
[37] X. C. Q. F. K. G. a. P. T. B. Zhou, "Garment modeling from a single image,"
Computer Graphics Forum, p. 85–91.
[38] E. I. G. P.-M. Verica Lazova, "360-Degree Textures of People in Clothing
from a Single Image," Computer Vision and Pattern Recognition, vol. 1, pp.
6-9, 20 Aug 2019.
[39] Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen, "Progressive
Growing of GANs for Improved Quality, Stability, and Variation," Neural and
Evolutionary Computing, 2018.
[40] R. G. A. Chattopadhyay, "Artificial neural networks: applications to
textiles. Textile Progress," p. 1–46, 2004.
[41] S. R. J. M. Mani Naik, "Fashion Advisor using Generative Adversarial
Networks," International Research Journal of Engineering and Technology
(IRJET), vol. 07, no. 05, pp. 1630-1642, 2020.
[42] Z. W. Z. W. R. Y. a. L. S. D. X. Han, "Viton: An image-based virtual try-
on network," in In Proceedings of IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), 2018.

View publication stats