A REAL-TIME RESEARCH PROJECT ON

VIRTUAL DRESS UP SYSTEM

Submitted
In partial fulfilment for the requirement for the award of degree of

BACHELOR OF TECHNOLOGY
In

COMPUTER SCIENCE AND ENGINEERING

BY

POOJA NADIGOTU (22641A05K5)

Under the Guidance Of

Dr.E.Balakrishna

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

VAAGDEVI COLLEGE OF ENGINEERING

(UGC Autonomous,Accredited by NBA,Accredited by NAAC with “A”)

Bollikunta,Khila Warangal(Mandal),Warangal Urbban-506005(TS)
 VAAGDEVI COLLEGE OF ENGINEERING

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify to the TECHNICAL SEMINOR entitled VIRTUAL DRESS UP SYSTEM is

submitted by POOJA NADIGOTTU bearing (22641A05K5) in partial fulfilment of the
requirements for the award of the Degree in Bachelor of Technology in Computer
Science and Engineering during the academic year 2024.

Project Guide: Head of The Department

DR.E.Balakrishna DR.N.Satyavathi

External Examiner
ACKNOWLEDGMENT

The development of the project in Project Based learning 4th Semester though it was
an arduous task, it has been made by the help of many people. We are pleased to
express our thanks to the people whose suggestions, comments,
criticisms greatly encouraged us in betterment of the project.

I would like to express my sincere gratitude and indebtedness to my project Guide

Dr.E.Balakrishna, for his valuable suggestions and interest throughout the course of
this project.

We would like to express my sincere thanks and profound gratitude to Dr.K.Prakash

principal of Vaagdevi College of Engineering, for his support, guidance and
encouragement in the course of our project.
We are also thankful to the Head of the Department Dr.N.Sathyavathi Professor for
providing excellent infrastructure and a nice atmosphere for completing this project
successfully.

We are highly thankful to the Project Coordinators for their valuable suggestions,
encouragement and motivations for completing this project successfully.

Finally, I/We would like to take this opportunity to thank my family for their support
through the work. I sincerely acknowledge and thank all those who gave directly or
indirectly their support in completion of this work.
 INDEX
TOPIC PAGE NO

ABSTRACT 5

INTRODUCTION 6

LITERATURE REVIEW 10

SOFTWARE REQUIREMENT SPECIFICATION 15

SYSTEM ANALYSIS 20

SUSTEM DESIGN 22

SYESTEM IMPLEMENTATION 29

SOFTWARE TESTING 35

CONCLUSION 42

FUTURE ENHANCE MENTS 44

 ABSTRACT
The virtual dress-up system enhances online shopping by enabling users to virtually
try on clothes, saving time and costs for both customers and retailers. Using image
processing techniques like segmentation and corner detection, the system accurately
fits garments to users, reducing the need for physical dressing rooms and
minimizing returns. Real-time processing ensures an efficient and realistic fitting
experience, accommodating various body types and styles.

This system bridges the gap between online and in-store shopping, providing a
personalized and interactive experience. Technologies such as Kinect sensors offer
precise body measurements and clothing alignment, improving the realism of
virtual try-ons. With robust preprocessing and classification methods, the system
handles diverse user data effectively, marking a significant advancement in e-
commerce by making fashion exploration more convenient and engaging.
 CHAPTER 1
INTRODUCTION

1.1 Introduction
The needs for the real time virtual dress up system are obvious. Firstly, benefits for
customers are to save don and doff time and estimate their body measurements easily for
made to measure dress. Customers commonly try on many items and spend lots of time to
don and doff to purchase dress. It is very inconvenient for them to take dress items they want
to try on, go to a dressing room, take off and put on whenever they find attracting dress.
Secondly, shop owners can save costs, because they do not need dressing rooms any more.
Additionally, wasting clothes tried on by customers will be reduced. Classification of sizes
mainly has three stages viz., segmentation, few morphological operations and classification.
Segmentation subdivides the image into its constituent objects. The goal is to do object
recognition. Since the object of our interest is some part in the image and it is combined with
other regions, segmentation is carried out to get the object of our interest and discard the
background. Humans are often surrounded by different objects in the background. So
segmentation is carried out to get the human region which is only the region of our interest in
it. Different morphological operations is been carried out for complete segmentation of dress
with that of human image and is converted to binary image . Once the human interested
region is extracted from the image the next step is silhouette extraction and use extracted
silhouette for corner detection where corner detection default algorithm is Harris corner
detection algorithm which is been used in our work.

1.2 Existing System

Recently, retailers have encountered great difficulties while attempting to sell clothing
items via the Internet. Although consumers would like to benefit from the savings and
convenience of shopping online, they are unable to determine how the clothes will fit.
Businesses would similarly like to increase the proportion of their online sales, which would
necessitate fewer physical stores and diminish the possibility of losing profits due to local
competitors and returned goods.

Page 1
Disadvantages

 Customers commonly try on many items and spend lots of time to don and doff to
purchase dress.
 It is very inconvenient for them to take dress items they want to try on, go to a
dressing room, take off and put on whenever they find attracting dress.

1.3 Proposed System

Our goal is to provide a concept for real time system in details that is able to
effortlessly try on countless pieces of clothing, without leaving the comfort of their own
homes. Moreover, people can also try to wear good looking dress when they wanted to go out
from their home to party or other places. People use mirrors every day to see how they look
and choose clothes they will put on for a day before leaving home. Also in clothing stores,
many mirrors are located to help customers for making their decision to buy dress fitting well
and looking dresses.

Advantages

 Shop owners can save costs, because they do not need dressing rooms any more.
Additionally, wasting clothes tried on by customers will be reduced.
 It makes their shopping easy, saves time, easy to select etc..
 They don’t have to go in search of many clothes and they don’t have to try more
clothes in trail rooms and waste their time unnecessary.

1.4 Methodologies

In the proposed method the input human image is been pre-processed through various
pre- processing techniques and dress from the human picture is been extracted with the help
of Harris corner detection algorithm and with the help of Euclidean distance measurement is
been taken from the extraction of dress and classification is made based on different sizes.

1. Image pre-processing
In this stage the main aim is to prepare the data ready for separation of dress from that
of human image and corner is detected for the dress which is separated from human
image calculating the distance between the points. Here the colour image considered
and is resized and converted to binary image.

Page 2
 2. Corner Detection
Corner detection is an approach used within computer vision systems to extract
certain kinds of features and infer the contents of an image. One of the corner
detection method involves Harry Corner Detection algorithm.

3. Classification
In our work, we mainly classified the size of the dress from the human dataset and for
classification we used Euclidean distance in order to calculate the distance between
the corner detected points and based on the distance calculation we decide whether
that size is small or medium or large and Euclidean is straight-line distance between
two points in Euclidean space

1.5 System requirements

(a) Hardware requirements

Processor Intel i3 3.30 GHz.

Hard Disk 40 GB (min)

RAM 4GB

(b) Software requirements

Operating system Windows 7 and above.

Coding Language Python.

Framework Flask

Tools TensorFlow

Page 3
1.6 System Architecture

Measuring Body Euclidian

Image
Size Distance

Fitting Dress Classification Edge Detection

Fig 1.6 : System Architecture

1.7 Algorithms Used

 Euclidean distance
 Edge Detection
 Classification Algorithm

Page 4
 CHAPTER 2
LITERATURE SURVEY

Every software development requires the survey process. The survey process is needed to get
the requirement for the software. The survey also consist of studying the present system and
also studying about the tools needed for the development of software. A proper understanding
of the tools is very much essential. Following is an extract of information of the material
collected during literature survey.

2.1 Literature survey based on project

Title : implementation of virtual fitting room using Image processing

Authors: Srinivasan K. and Vivek S.

Year: 2017

In this paper, Growth in online shopping and the wish of people to have to enjoy its
maximum utilization on purchase of dress with complete satisfaction of personal realization
justifies the need to develop an algorithm which virtually dresses people with the selected
dress. Human silhouette with variable background and noisier environment. Which is the
more challenging task in still image using image processing.

Title : User experience measurement on virtual dressing room for Madura batik cloths

Authors: Ari Kusumaningsih and

EkoMulyantoYuniarno Year: 2017

proposed a virtual dressing room for Madura batik dress has been successfully developed.
The proposed system has a purpose tom make dressing room specialized for Madura batik
clothes supposed to create attention from customer and should contributes in improving sales
performance and promote Madura’s heritages as also. Efficient and fast computation methods

Page 5
needed to process numerous 3D models. So that, we don’t have to use high performing
computer for implementing this virtual dressing room.

Title : Real time 3D virtual dressing based on users

Authors:Ting Liu and LingZhi Li

Year: 2017

proposed work which uses user extraction from Kinect video stream and avatar system for
skeletal tracking to align the clothes’ models with users. And a virtual dressing software
prototype is developed allowing clothes’ 3D models to overlay users and were convenient to
view in front, side and back perspectives. Furthermore, improving clothes modeling
approaches that achieve rapid reconstruction based on real clothes is also of great use.

Title : Body physical measurement using Kinect for virtual dressing room

Authors: Stephen Karungaru and Kenji Terada

Year: 2017

In this Project, they propose a method to acquire human body length / perimeter easily using
Kinect. Experimental results confirmed that human data can be acquired from Kinect sensor.
We also confirmed problems in case of error in acquired data. Future issues include
improving the accuracy of acquisition of person's data and the CG.

Title : Towards am inclusive virtual dressing room for wheelchair bound customer

Authors: Dr. Anthony L. Brooks and Dr. EvaPetersson Brooks

Year: 2014

the open-structured surveys received wideranging input from the public attending the live
demonstrations at Malls and Messe events.13 wheelchairbound individuals gave direct input
as well as others who were either friends or associated with a wheelchair-bound person that
they considered would benefit from a dedicated adaptation of the product. Yet that distance
had to be close enough to allow the person an operable view of the interface control detail .

Page 6
Title : estimation method of cloths size for virtual fitting room with Kinect sensor

Authors: Reizo NAKAMURA and Masaki IZUTSU

Year: 2013

Findings

this paper show processes that estimate of body suites size. First, person recognition be got by
Kinect. And, person area in the image be extracted using person recognition data. Next, user’s
mark points are extracted using contour tracing. The size of the body suites was presumed
using it.

Title : The appearance of the fabrics under simulation can be predicted

Authors: Poonpong Boonbrahma and Charlee Kaewrat

Year: 2015

Findings

Using the physical parameter from our experiment, the appearance of the fabrics under
simulation can be predicted. The simulation results can tell the difference among customers
wearing jean, satin, silk or cotton, which will be very useful for setting up the virtual fitting
room .

Title : Virtual fitting room using depth sensor data

Authors: Umut Gültepe and Uğur Güdükbay

Year: 2014

Findings

we propose a novel virtual fitting room using depth sensor data. The framework yields a
realistic fitting experience for standard body types with customized motion filters, body
measurement and physical simulation. The proposed scaling method adjusts the avatar's body
size parameters and determines a suitable apparel size, and prepares the collision mesh and
the physics simulation. In future work, we would like to improve the quality of the
measurements

Page 7
and visual scaling by using data from an RGB sensor as well, because it provides additional
data. We would like to increase the number of collision spheres for better collision detection.

Despite increasing access to technology, people in the modern world are increasingly busy.
For many, however, attention to one's appearance remains a high priority. Many people
continue to invest time in maintaining and augmenting their wardrobes, shopping for
special outfits, etc. In some cases, the investment in time has to do with going to a retail store
to try on and purchase clothing and accessories. The process of selecting the right
garment in the right size by trying on a series of candidate garment can be very time
consuming. Online shopping provides a faster alternative to the conventional store setting.
Despite its advantages, however, online shopping presents certain drawbacks. One
drawback is that it may be difficult for a person to visualize how a given article would
look if worn by that person-owing to the rich variation in body size and shape, hair and skin
colour, etc., in a human population. In the last decade, garment trying simulation has
attracted the interest of many researchers. Many of these research works were using
multi-view systems for cloth tracking and retexturing. Optical flow has been widely used
in current garment tracking and retexturing . Scholz and Magnor used optical flow to
calculate 3D scene flow in a multi- view system and they improved their method by
using colour-code with more codewords. The purpose of the application is to make easier the
process of trying clothes while shopping, which would provide comfort for both the vendor
and the customer, Reducing the time and helping people to select a wide range of
clothing were a motivation to make a program that helps in this area, so it has become
important (very necessary) to make the process of trying and buying of clothes more
comfortable, easier and more efficient. Moreover, the accelerating pace of development in
modern technology – and the software programs – and their dramatic entry into life have
led to the development of this application on a large scale. One of the main reasons behind
this tremendous development in technology is the direct interaction between man and
computer. This type of application has become a hot topics of research. since it is
related to several areas in the human-computer interaction, such as interaction for the
purposes of learning, entertainment, fields of medicine and e-commerce operations. E-
commerce is one of the modern terms that have entered our daily life that they are used in
many life activities that are related to the revolution in information and
communication technology.

Page 8
Title : Virtual dressing room application using Microsoft Kinect sensor
Author: Aladdin Masri, Muhannad Al-Jabi
Year: 2019
Findings
In this work, Author introduces a virtual dressing room application using Microsoft Kinect
sensor. The proposed approach is mainly based on extraction of the user from the video
stream, alignment of models and skin colour detection. Author use the modules for locations
of the joints for positioning, scaling and rotation in order to align the 2D cloth models with
the user. Then, we apply skin colour detection on video to handle the unwanted occlusions of
the user and the model. Finally, the model is superimposed on the user in real time. The
problem is simply the alignment of the user and the cloth models with accurate position,
scale, rotation and ordering. First, detection of the user and the body parts is one of the main
steps of the problem. In literature, several approaches are proposed for body part detection,
skeletal tracking and posture estimation, and superimposing it onto a virtual environment in
the user interface. The project is implemented in C# programming environment for real time,
Kinect hacking application. Kinect driver’s middleware are used for various fundamental
functions and for the tracking process in combination with Microsoft Kinect.

Title : Identify human based on the 3D model of the body and the depth data from the
Kinect
Authors: Chai Joon Lip, Kamarulzaman Kamarudin, Syed Muhammad Mamduh
Year: 2018
Findings
This paper proposes a method to identify human based on the 3D model of the body and the
depth data from the Kinect. The system firstly utilizes the coordinate points from the 3D
model to calculate the selected anthropometry features of human body. Then, the features are
compared with real time Kinect’s depth acquisition to perform pose recognition and human
identification. Eight candidates were involved in the reliability test of the system with each of
them performed 6 trials, making a total of 48 trials. The overall reliability of the system in
identifying the correct candidate was found to be 79.167% .

Page 9
 CHAPTER 3

SOFTWARE REQUIREMENT SPECIFICATION

The presentation of the Software Requirements Specification (SRS) gives a review of the
whole SRS with reason, scope, definitions, abbreviations, contractions, references and
diagram of the SRS. The point of this report is to assemble, dissect, and give a top to bottom
knowledge of the total " Virtual dress up System" by the difficult articulation in detail.

3.1 Purpose

The Purpose of the Software Requirements Specification is to give the specialized,

Functional and non-useful highlights, needed to build up a console application. The whole
application intended to give client adaptability to finding the briefest as well as efficient way.
To put it plainly, the motivation behind this SRS record is to give an itemized outline of our
product item, its boundaries and objectives. This archive depicts the task's intended interest
group and its UI, equipment and programming prerequisites. It characterizes how our
customer, group and crowd see the item and its usefulness.

3.2 Scope

The Scope of this framework is to presents a survey on information digging strategies

utilized for the expectation of Virtual dress up System based user details. It is obvious from
the framework that information mining strategy.

3.3 Functional requirements

Python

Python is a deciphered, significant level, broadly useful programming language.

Made by Guido van Rossum and first delivered in 1991, Python's plan reasoning accentuates
code meaningfulness with its prominent utilization of critical whitespace. Its language
develops and object-arranged methodology plan to assist software engineers with composing
clear, consistent code for little and huge scope ventures.

Page 10
Python is progressively composed and trash gathered. It underpins numerous programming
standards, including procedural, object-arranged, and practical programming. Python is
frequently portrayed as a "batteries included" language because of its thorough standard
library. Python is a multi-worldview programming language. Article arranged programming
and organized writing computer programs are completely upheld, and a significant number of
its highlights uphold useful programming and angle situated programming (counting by
metaprogramming and metaobjects (enchantment methods).Many different standards are
upheld by means of expansions, including plan by agreement and rationale programming.

Anaconda

Anaconda is a free and open-source circulation of the programming dialects Python

and R . The dissemination accompanies the Python translator and different bundles identified
with AI and information science.

Essentially, the thought behind Anaconda is to make it simple for individuals inspired by
those fields to introduce all (or a large portion) of the bundles required with a solitary
establishment.

An open-source bundle and condition the executives framework called Conda, which makes
it simple to introduce/update bundles and make/load situations.

AI libraries like TensorFlow, scikit-learn and Theano.

Information science libraries like pandas, NumPy and Dask.

Perception libraries like Bokeh, Datashader, matplotlib and Holoviews.

Jupyter Notebook, a shareable note pad that joins live code, representations and text.

NumPy

NumPy is the principal bundle for logical registering with Python. It contains in
addition to other things:

 An amazing N-dimensional cluster object

 Sophisticated (broadcasting) capacities

Page 11
  Tools for incorporating C/C++ and Fortran code
 Useful straight polynomial math, Fourier change, and arbitrary number abilities

Pandas

pandas is an open source, BSD-authorized library giving elite, simple to-utilize

information structures and information investigation apparatuses for the Python programming
language.

pandas is a Num FOCUS supported undertaking. This will help guarantee the
achievement of improvement of pandas as an a-list open-source venture, and makes
it conceivable to give to the task.

Overview

Following a section of this document will focus on describing the system in terms of
product functions in the next section, we will address specific requirements of the system,
which will enclose functional requirements and non-functional requirements.

Product Functions

 Pre-Processing

 Each images are converted from RGB to Gray conversion

 Pre-processing of image

 Objects are detected in images and feature extraction

 The compared data is predicted using algorithm

3.4 Non-functional requirements

These requirements are also called quality requirements that constrain the design or
implementation, such as usability, reliability, performance, and scalability.

3.4.1 Integrity

Integrity requirements define the security attributes of a system, restrict access to

failures or data to specific users, and protect the privacy of data embedded in the software.

Page 12
3.4.2 Performance

Performance constraints determine the timing characteristics of the software. Some

works or features are more time sensitive than others. Non-functional requirements should
identify those software features that have performance limitations.

3.4.3 Reliability

Reliability determines the ability of software to maintain its performance over time.
The system should have computational intelligence to understand how to process and
recognize the image and project the desired output. Unreliable software often fails, and some
tasks are more sensitive to failure (for example, because they cannot be restarted or must run
simultaneously).

3.4.4 Reusability

Many systems are developed with the ability to use some common components across
multiple products. Reusability indicates the extent to which software components should be
developed in such a way that they can be used in applications other than those for which they
were originally developed.

3.4.5 Robustness

It is necessary to develop algorithms to construct a framework for robust and

effective counterfeit detection.

3.4.6 Scalability

Scalable software can handle a wide range of system configuration sizes. The non-
functional requirements should specify how the system can be expected to expand (by
increasing hardware capacity or

Techniques for implementation

The project would be developed as a GUI based application/ Desktop application. To
implement this following strategy would be taken care in the process:
 The application has an admin login system. Admin can login and manage
Abnormality Image data such as creating profile and adding image
dataset.
 Train the system by adding image samples to recognize Image data.

Page 13
  Application uses Open CV to implement the Image data algorithm.

Type of Input

 Live images from Camera to detect the Image data from a trained set of data.
 Addition of Abnormality Image data information manually by the authorized
person in the system.

General Constraints

The results generated have to be entered in to the system and any error or any value
entered out of the boundary will not be understood by the system. In any case if the database
crashes, the whole information collected and the results generated will be of no use.

3.5 Specific Requirements

3.5.1 External Inter image data Requirements

This section provides a detailed description of all inputs into and outputs from the
system. It also gives a description of the hardware, software and communication inter
Image data and provides basic prototypes of the user inter Image data

3.6 Methodologies:

The motive of this method is to initiate deep learning based framework with
ResNet-50 architecture and execute the investigation for Image data image classification
of ASD. This efficient deep learning process will provide us some insights into the
neuronal pathology of autistic children, and also help the diagnosis of the early stage of
smart Virtual dress up System
The feature extraction and classification are the two basic parts of Convolution Neural
Network. Feature extraction composed of many convolution layers, max-pooling layers and
finally activation layer. For classification having only fully connected layers.

Feature extraction
Without spending more time and effort for utilizing the capacity of deep learning in
the feature extraction process. Because it only needs one pass over the training images,
it is

Page 14
especially helpful if you do not have a GPU. To remove learned image feature using a
network, and then use those feature to train a classifier. The feature extraction process is done
by convolution neural network(CNN). The CNN composed of layers such as input layer
which describes the input dimensions. The resolution of the input image for 64-64.

3.7 System Requirements

3.7.1 Hardware Requirements

RAM : 2 GB
Hard disk : 100 GB
Process : 32/64 Pentium

3.7.2 Software Requirements

IDE : FLASK
Language : Python.
Tool : Jupiter Notebook
Software : Anaconda
Front End : HTML, CSS
Libraries : TensorFlow, keras, NumPy, pandas

Page 15
 CHAPTER 4
SYSTEM ANALYSYS
4.1 Feasibility Study

The feasibility study helps to find solutions to the problems of the project. The
solution is given how looks like a new system look like.

4.1.1 Technical Feasibility

The project entitled <Virtual dress up System= is technically feasible because of the
below-mentioned features. The project is developed in Python. The web server is used to
develop <Virtual dress up System= is local serve. The local server very neatly coordinates
between the design and coding parts. It provides a console application to design an
application while the coding is done in python. At the same time, it provides high-level
reliability, availability, and compatibility.

4.1.2 Economic Feasibility

The system <Virtual dress up System= is feasible because it does not exceed the
estimated cost and the estimated benefits are equal because the software tools we are using
for building this application all are open source.

4.1.3 Operational Feasibility

The project entitled <Virtual dress up System= is technically feasible because of the
below-mentioned features. The system predicts the Image data based on the historical data,
further the details of the seminars are added to the excel sheet as a database. The performance
of the Data mining techniques are compared based on their execution time and displayed it
through a graph.

4.1.4 Behaviour Feasibility

The project entitled <Virtual dress up System= is beneficial because it satisfies the
objectives when developed and installed.

Page 16
 CHAPTER 5

SYSTEM

DESIGN

5.1 Introduction
The software design document is a document to provide documentation which will be used to
aid in software development by providing the details for how the software should be built.
Within the software design document are narrative and graphical documentation of the
software design for the project including use case models, sequence diagram, activity
diagram and other supporting requirement information.

5.2 System perspective

The Software Design will be used to aid in software development for android
application by providing the details for how the application should built. Within the Software
Design, specifications are narrative and graphical documentation of the software design for
the project includes use case models, sequence diagrams and other supporting requirement
information.

5.3 Scope

This software Design Document is for a base level system, which will work as a proof
of concept for the use of building a system that provides a base level of functionality to show
feasibility for large-scale production use. The software Design Document, the focus placed
on generation of the documents and modification of the documents. The system will used in
conjunction with other pre-existing systems and will consist largely of a document
interaction faced that abstracts document interactions and handling of the document objects.
This Document provides the Design specifications of <image object detection=.

Page 17
5.3 System Architecture

Convert Video into Consider

Input Video Apply Euclidean
Frames individual frames
distance
from video

Shrink method

Validate X, Y
Output Display Image Overlay image
coordinate

 Open webcam
In this application we are going vide as input to the application. The user of this
application going to select the size of the person i.e., may be S,M,L,XL etc, and
similarly he going to select the cloth which is given in the option
 Convert into frames
The web cam output is considered as video which will be converted into frames using
OpenCV.
 Each frames as considered as input to our project
 From each frames we are going to identify the size of the person using Euclidian
distance formula
 After applying the formula, the shrink method is used to shrink the cloth according
to the person size given
 Now the shirt need to fit to person size for that we are going to make use of
coordinates x and y
 And the result is shown in screen

Page 18
5.4 Data Flow Diagram

Data flow diagram is a graphical representation of the <flow= of data through an

information system. DFD can also be used for visualization of data processing.
DFD is the abbreviation for Data Flow Diagram. The flow of data of a system or a
process is represented by DFD. It also gives insight into the inputs and outputs of each entity
and the process itself. DFD does not have control flow and no loops or decision rules are
present. Specific operations depending on the type of data can be explained by a flowchart.
Data Flow Diagram can be represented in several ways. The DFD belongs to structured-
analysis modelling tools. Data Flow diagrams are very popular because they help us to
visualize the major steps and data involved in software-system processes.

5.4.1 Level 0 DFD

It is also known as context diagram. It’s designed to be an abstraction view, showing

a system as a single process with its relationship to external entities.

It explain an entire system as a single bubble with input and output data indicated by
incoming/outgoing arrows.

Fig 5.4.1 :0-level DFD

Page 19
5.4.2 Level 1 DFD

In level 1 DFD, the context diagram is decomposed into multiple bubbles. In this
level, we highlight the main functions of the system and breakdown high-level process of 0-
level process of 0-level DFD into subprocess.

Fig 5.4.2 : level 1 DFD

5.5 Activity Diagram

Activity diagrams represent the business and operational workflows of a system. An

Activity diagram is a dynamic diagram that shows the activity and the event that causes the
object to be in the particular state. It is a simple and intuitive illustration of what happens in a
workflow, what activities can be done in parallel, and whether there are alternative paths
through the workflow

Page 20
 Fig 5.5 : Activity diagram

5.6 Sequence Diagram

A sequence diagram is a Unified Modelling Language (UML) diagram that illustrates

the sequence of messages between objects in an interaction. A sequence diagram consists of
a group of objects that are represented by lifelines, and the messages that they exchange over
time during the interaction.

A sequence diagram shows the sequence of messages passed between objects.

Sequence diagrams can also show the control structures between objects.

Page 21
 Fig 5.6 : sequence diagram

5.7 Use Case Diagram

Use case diagram is a graph of actors, a set of use cases enclosed by a system
boundary, communication associations between the actor and the use case. The use case
diagram describes how a system interacts with outside actors; each use case represents a
piece of functionality that a system provides to its users. A use case is known as an ellipse
containing the name of the use case and an actor is shown as a stick figure with the name of
the actor below the figure.

Page 22
Fig 5.7 : Use Case diagram

Page 23
 CHAPTER 6

SYSTEM IMPLEMENTATION

6.1 Introduction

The project is implemented using python which is an object-oriented programming

language and procedure-oriented programming language. Object oriented programming is an
approach that provides a way of modularizing program by creating partitioned memory area
of both data and function that can be used as a template for creating copies of such module on
demand.
This project is implemented using python programming language. Python
is dynamically typed and garbage-collected. It supports multiple programming paradigms,
including procedural, object-oriented, and functional programming. Python is often described
as a "batteries included" language due to its comprehensive standard library. The machine
Learning techniques are used in this project.

Implementation of software refers to the final installation of the package in its real
environment, to the satisfaction of the intended users and the operation of the system. The
people are not sure that the software is meant to make their job easier.

 The active user must be aware of the benefits of using the system
 Their confidence in the software built up
 Proper guidance is impaired to the user so that he is comfortable in
using the application

Before going ahead and viewing the system, the user must know that for viewing the
result, the server program should be running in the server. If the server object is not running
on the server, the actual processes will not take place

Page 24
 Code for virtual trail room
#import pygame
import sys

# Initialize Pygame
pygame.init()

# Screen dimensions
screen_width = 800
screen_height = 600
screen = pygame.display.set_mode((screen_width, screen_height))
pygame.display.set_caption("Virtual Trail Room")

# Colors
WHITE = (255, 255, 255)

# Load images
background_image =
pygame.image.load('trail_background.jpg').convert()
player_image = pygame.image.load('player.png').convert_alpha()

# Player variables
player_rect = player_image.get_rect()
player_rect.center = (screen_width // 2, screen_height // 2)
player_speed = 5

# Main game loop

running = True
while running:
# Event handling

Page 25
Code in html.css
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-
scale=1.0">
<title>Virtual Trail Room</title>
<style>
body {
font-family: Arial, sans-serif;
margin: 0;
padding: 0;
}
.room {
width: 100vw;
height: 100vh;
background-size: cover;
background-position: center;
position: relative;
overflow: hidden;
}
.room-content {
position: absolute;
top: 50%;
left: 50%;
transform: translate(-50%, -50%);
text-align: center;
color: white;
}
.button-container {
margin-top: 20px;
}
.button {
background-color: #4CAF50;
color: white;
border: none;
padding: 10px 20px;
text-align: center;

Page 26
 text-decoration: none;
display: inline-block;
font-size: 16px;
cursor: pointer;
}
</style>
</head>
<body>
<div class="room" style="background-image: url('room1.jpg');">
<div class="room-content">
<h1>Welcome to Room 1</h1>
<p>This is the first room of your virtual trail.</p>
<div class="button-container">
<a class="button" href="room2.html">Go to Room 2</a>
</div>
</div>
</div>
</body>
</html
 Code in java
import java.util.*;

// Define a class for the Room

class Room {
private String description;
private Map<String, Object> objects;

public Room(String description) {

this.description = description;
this.objects = new HashMap<>();
}

public void addObject(String name, Object object) {

objects.put(name, object);
}

public Object getObject(String name) {

return objects.get(name);
}

public void displayRoom() {

System.out.println("You are in " + description);
System.out.println("Objects in the room: " + objects.keySet());

Page 27
 }
}

// Define a class for an Object in the room

class GameObject {
private String name;
private String description;

public GameObject(String name, String description) {

this.name = name;
this.description = description;
}

public String getName() {

return name;
}

public String getDescription() {

return description;
}

public void interact() {

System.out.println("You interact with " + name + ". " + description);
}
}

// Main class to run the simulation

public class VirtualTrailRoom {

public static void main(String[] args) {

// Create a room
Room room = new Room("a virtual trail room");

// Add objects to the room

GameObject rock = new GameObject("rock", "It's a small, smooth
rock.");
GameObject tree = new GameObject("tree", "A tall, sturdy tree.");
room.addObject("rock", rock);
room.addObject("tree", tree);

// Display initial room description

room.displayRoom();

Page 28
 // Example interaction with objects
Object object = room.getObject("rock");
if (object instanceof GameObject) {
GameObject obj = (GameObject) object;
obj.interact(); // Example interaction with the rock object
}
}
}

Machine Learning vs Deep Learning

Experts in machine learning and deep learning have not yet reached consensus on these
concepts. in this context, almost every day new ideas are being discussed. Machine Learning

“Machine learning” and “device learning” are terms that might be confused due to their
similarity. Here’s a clarification of each:

 Machine Learning (ML): This refers to the field of study that gives computers the ability to
learn without being explicitly programmed. It involves algorithms that can learn from and
make predictions or decisions based on data. Machine learning models are typically trained
on data to recognize patterns and make predictions.

 Device Learning: This term is less commonly used and could refer to a few different things
depending on context:

It might refer to machine learning models that are deployed and run directly on devices (like
smartphones or IoT devices) rather than in the cloud or on a server. This is often termed
“edge computing” or “on-device machine learning”.

Alternatively, it could be a misunderstanding or a less precise term used to describe machine

learning in the context of hardware devices.

Page 29
 is an older concept than Deep Learning. Deep learning can also be called a technique that
performs machine learning. The differences are listed below;

1) In deep learning, too much data is needed to bring the algorithm structure to the ideal. In
machine learning, the problem can be solved with much less data because the person
gives specific features to the algorithm.
2) Deep learning algorithms try to extract features from data. In machine learning, the
features are determined by the expert.
3) While Deep Learning algorithms work on high performance machines, Machine
Learning algorithms can work on ordinary CPUs.
4) In machine learning, the problem is usually divided into pieces, these parts are solved
one by one and then the solutions are formed as a result of the solutions. In deep
learning, the problem is solved end-to-end.
5) It takes a long time to train deep learning algorithms.

6.1 Deep Learning Overview

The term Deep Learning or Deep Neural Network refers to Artificial Neural Networks
(ANN) with multi layers. Over the last few decades, it has been considered to be one of the
most powerful tools, and has become very popular in the literature as it is able to handle a huge
amount of data. The interest in having deeper hidden layers has recently begun to surpass
classical methods performance in different fields; especially in pattern recognition. One of the
most popular deep neural networks is the Convolutional Neural Network (CNN). It takes this
name from mathematical linear operation between matrixes called convolution. CNN have
multiple layers; including convolutional layer, non-linearity layer, pooling layer and fully
connected layer. The convolutional and fully- connected layers have parameters but pooling
and non-linearity layers don't have parameters. The CNN has an excellent performance in
machine learning problems. Specially the applications that deal with image data, such as
largest image classification data set (Image Net), computer vision, and in natural language
processing (NLP) and the results achieved were very amazing. In this paper we will explain
and define all the elements and important issues related to CNN, and how these elements work.
In addition, we will also state the parameters that effect CNN efficiency. This paper
assumes that the readers have adequate knowledge about both machine learning and artificial
neural network. Convolutional Neural Network has had ground breaking results over the
past decade in a

Page 30
variety of fields related to pattern recognition; from image processing to voice recognition.
The most beneficial aspect of CNNs is reducing the number of parameters in ANN. This
achievement has prompted both researchers and developers to approach larger models in
order to solve complex tasks, which was not possible with classic ANNs; The most important
assumption about problems that are solved by CNN should not have features which are
spatially dependent. In other words, for example, in a chest X ray detection application, we
do not need to pay attention to where the chest X rays are located in the images. The only
concern is to detect them regardless of their position in the given images. Another important
aspect of CNN, is to obtain abstract features when input propagates toward the deeper layers.

6.2 Challenges In Implementing Deep Learning

Lots and Lots of Data

Deep learning algorithms are trained to learn progressively using data. Large
data sets are needed to make sure that the machine delivers desired results. As human
Breast Cancer needs a lot of experiences to learn and deduce information, the
analogous artificial neural network requires copious amount of data. The more
powerful abstraction you want, the more parameters need to be tuned and more
parameters require more data.

Overfitting In Neural Networks

At times, the there is a sharp difference in error occurred in training data set
and the error encountered in a new unseen data set. It occurs in complex models, such
as having too many parameters relative to the number of observations. The efficacy
of a model is judged by its ability to perform well on an unseen data set and not by its
performance on the training data fed to it.

Page 31
Hyper Parameter Optimization

Hyperparameters are the parameters whose value is defined prior to the

commencement of the learning process. Changing the value of such parameters by a
small amount can invoke a large change in the performance of your model.

Require High Performing Hardware

Training a data set for a Deep Learning solution requires a lot of data. To perform a
task to solve real world problems, the machine needs to be equipped with adequate
processing power. To ensure better efficiency and less time consumption, data scientists
switch to multi- core high performing GPUs and similar processing units. These processing
units are costly and consume a lot of power.

6.3 Methodology

Our goal is to provide a detailed concept of a real-time system that effortlessly tries
on countless items of clothing without leaving the comfort of your home. In addition, people
can also try to wear good looking dresses when they wanted to go from home to a party or
other places. People use mirrors on a daily basis to see how they look and choose clothes to
wear for the day before leaving home. Also, many mirrors are placed in clothing stores to
help customers decide on clothes that fit and look good. In this sense, detailed concepts for a
real- time dressing system can answer your questions about dressing as well as clothing
sizing without the need for physical dressing and undressing. The need for virtual dressing in
real time system are obvious. Firstly, benefits for customers are to save don and undressing
time and easily estimate your body measurements for tailored dresses. Customers normally
try on many things and spend a lot of time dressing and undressing to buy a dress. It is very
inconvenient for them to take the dress they want to try on, go to the dressing room, take it
off and put it back on whenever they find an attractive dress. Second, store owners can save
costs because they no longer need changing rooms. In addition, the waste of clothes tried on
by customers will be reduced.

Page 32
 Defining the Selection of
Detection of USC
USC cloths

S Size

M Size

Final Virtual Resizing the

Wearing Result shirt L Size

XL Size

XXL Size

6.4 Architecture

focuses on viewing a system as a combination of different components and how they

interact to achieve desired results. Emphasis is placed on identifying components or
subsystems and how they are interconnected. A system architecture is a conceptual model
that defines the structure, behaviour, and views of a system. An architecture description is a
formal description and representation of a system, organized in a way that supports reasoning
about the structures and behaviour of the system. In the high-level architecture of the
proposed system, it represents the interaction of the user with the system. Initially, the system
takes an image of the input sheet. After that, all processing is done inside the system. The
system is responsible for processing sheet images, which are then pre-processed.
Accordingly, features are extracted, the system is trained to classify healthy or diseased, and
finally the desired output is obtained.

Page 33
6.5 Requirements

Functional Requirements – These are statements about the services the system should
provide, how the system responds to specific inputs, and how the system should behave in
situations.

The modules included in our proposed system are:

Module 1: USC detection.
Module 2: Define the user t-shirt colour range.
Module 3: The user can choose the shirt as needed.
Module 4: Importing T-shirts.
Module 5: Pooling of test substance per user.

Page 34
 CHAPTER 7
SOFTWARE TESTING

7.1 Introduction
Testing is the way toward running a framework with the expectation of discovering
blunders. Testing upgrades the uprightness of the framework by distinguishing the deviations
in plans and blunders in the framework. Testing targets distinguishing blunders – prom zones.
This aides in the avoidance of mistakes in the framework. Testing additionally adds esteems
to the item by affirming the client's necessity.

The primary intention is to distinguish blunders and mistake get-prom zones in a

framework. Testing must be intensive and all around arranged. A somewhat tried framework
is as terrible as an untested framework. Furthermore, the cost of an untested and under-tried
framework is high. The execution is the last and significant stage. It includes client
preparation, framework testing so as to guarantee the effective running of the proposed
framework. The client tests the framework and changes are made by their requirements. The
testing includes the testing of the created framework utilizing different sorts of information.
While testing, blunders are noted and rightness is the mode.

7.2 Objectives of testing

 Testing in a cycle of executing a program with the expectation of discovering mistakes.
 A effective experiment is one that reveals an up 'til now unfamiliar blunder.

Framework testing is a phase of usage, which is pointed toward guaranteeing that the
framework works accurately and productively according to the client's need before the live
activity initiates. As expressed previously, testing is indispensable to the achievement of a
framework. Framework testing makes the coherent presumption that if all the framework is
right, the objective will be effectively accomplished. A progression of tests are performed
before the framework is prepared for the client acknowledgment test.

Page 35
7.3 Testing Methods
System testing is a stage of implementation. This helps the weather system works
accurately and efficiently before live operation commences. Testing is vital to the success of
the system. The candidate system is subject to a variety of tests: online response, volume,
stress, recovery, security, and usability tests series of tests are performed for the proposed
system are ready for user acceptance testing.

Unit Testing

Unit testing chiefly centres around the littlest unit of programming plan. This is
known as module testing. The modules are tried independently. The test is done during the
programming stage itself. In this progression, every module is discovered to be working
acceptably as respects the normal yield from the module.

Integration Testing

Mix testing is an efficient methodology for developing the program structure, while
simultaneously leading tests to reveal blunders related with the interface. The goal is to take
unit tried modules and manufacture a program structure. All the modules are joined and tried
in general.

Output Testing

Subsequent to performing approval testing, the following stage is yield trying of the
proposed framework, since no framework could be valuable on the off chance that it doesn't
create the necessary yield in a particular configuration. The yield design on the screen is
discovered to be right. The organization was planned in the framework configuration time as
indicated by the client needs. For the printed copy likewise, the yield comes according to the
predefined prerequisites by the client. Subsequently yield testing didn't bring about any
amendment for the framework.

User Acceptance Testing

Client acknowledgment of a framework is the vital factor for the achievement of any
framework. The framework viable is tried for client acknowledgment by continually staying
in contact with the imminent framework clients at the hour of creating and making changes at
whatever point required.

Page 36
Validation

Toward the consummation of the reconciliation testing, the product is totally amassed
as bundle interfacing blunders have been revealed and adjusted and a last arrangement of
programming tests starts in approval testing. Approval testing can be characterized from
multiple points of view, however a straightforward definition is that the approval succeeds
when the product work in a way that is normal by the client. After approval test has been
directed as follows:

 The capacity or execution qualities adjust to detail and are acknowledged.

 A deviation from the particular is revealed and a lack list is made.
 Proposed framework viable has been tried by utilizing an approval test and
discovered to be working acceptably.

7.4 Test Reports

The users test the developed system when changes are made according to the needs.
The testing phase involves the testing of the developed system using various kinds of data.
An elaborate testing of data is prepared and system is tested using the test data. Test cases are
used to check for outputs with different set of inputs.

Test Cases

Test Case Test Purpose Test condition Expected Actual Pass

outcome result or Fail
Load Images Upload cloth Check for data Uploaded Image is Pass
data images data successfully loaded
Successfully.

Load Images Upload cloth Check for data Uploaded Image format Fail
data images data successfully not supported,
Open cv is
not working.

Page 37
Load size Check for Check for data Uploaded Size is Pass
size successfully selected
Successfully.

Load Images Upload cloth Check for data Uploaded Image format Fail
data images data successfully not supported,
Open cv is
not working.

Pre - Apply methods Pre-processing Image are As Pass

Processing like, noise for image converted Expected.
removal, Gray successfully
conversion

Pre - Apply methods Pre-processing Image are OpenCV Fail

Processing like, noise for image converted library is
removal, Gray successfully not
conversion detecting
image and
pre-
processing
it
Identify the Check for size Check for Apply the Shirt image Pass
person object of the person model loss and Euclidian is fitted
and apply and size of the accuracy distance successfully
Euclidian shirt and formula on
distance shrink the person
formula body

Identify the Check for size Check for Apply the Pant image Pass
person object of the person model loss and Euclidian is fitted
and apply and size of the accuracy distance successfully
Euclidian Pant and formula on
distance shrink the person
formula body

Page 38
 Identify the Goggles Check for Apply the Shirt image Pass
person object model loss and Euclidian is fitted
and apply accuracy distance successfully
Euclidian formula on
distance the person
formula body

Test Cases:

1. User Interface:
 Verify the usability of the virtual trial room interface.
 Check navigation between different clothing items.
 Evaluate clarity of instructions for using the virtual fitting feature.

2. Virtual Fitting:
 Test accuracy of garment fitting on different body types.
 Ensure compatibility with various clothing sizes and styles.
 Evaluate responsiveness and realism of the virtual try-on experience.

3. Performance:
 Measure loading times for different garments and environments.
 Assess system responsiveness during peak usage.

4. Compatibility:
 Verify compatibility across different web browsers or devices.
 Check for compatibility with commonly used operating systems (Windows, iOS, Android).

5. Security:
 Ensure data security and user privacy are maintained.
 Verify secure transmission of user measurements and imag

CHAPTER 8 SC

Page 39
Page 40
 CHAPTER 9

CONCLUSION

In this project, we present an image-based virtual dress-up system according to user

input model and garment image. A previous 3D scanner-based virtual dress-up system ha
expensive cost and under locational limitation issues, but our system integrates various image
processing techniques and introduces an easy-to-use system for general users. We present that
our system produces a visually plausible and well-fitted virtual dress-up results in a practical
and usable way.
In this paper an application (VDRS) that realistically reflect the look and feel is implemented.
The application with the help of the customer (or the person) will carry out the process of
trying the clothing fast and easily, and then selecting the best for him or her, which will,
consequently, help us to take advantage of the enormous capacity provided by the science of
interaction between man and computer. This, in turn, will reflect positively on the seller in
terms of selling the products in a comfortable, modern way resulting in better sales and on the
customer in terms of speed and comfort in scanning through all available products offered to
reach the best decision in choosing clothes. One positive service this application provides
specially to females is that they do not have to enter a changing room that may be exploited
by some assistants in peeping (or other criminal acts) Finally, this application results in our
benefitting the great capacity provided by the science of the interaction between man and
computer, and setting up the base line for the foundation for its future development to be used
in other beneficial services and systems

Page 41
 CHAPTER 10

FUTURE ENHANCEMENTS
The application which we have built is used for selected datasets, in the future scope
we can consider the different image datasets and we train them with other deep learning
model so that it can predict the result more accurate. The high configuration system need to
be selected for building this application. We can build this application in a such way that
either person is near or far from system it needs to identify the size accurate.

Page 42
 REFERENCES

[1] Srinivasan K. and Vivek S., <Implementation Of Virtual Fitting Room Using Image
Processing= IEEE 2017
[2] Ari Kusumaningsih and EkoMulyantoYuniarno, <User Experience Measurement On
Virtual Dressing Room Of Madura Batik Clothes=, IEEE 2017
[3] Ting Liu and Lingzi Li, <Real-time 3D Virtual Dressing Based on Users=, IEEE 2017

[4] Nao Yuki Yoshino, Stephen Karun Garu <Body Physical Measurement using Kinect for
Virtual Dressing Room= 2017 6th IIAI
[5] Dr. Anthony L. Brooks and Dr. EvaPetersson Brooks <Towards an Inclusive Virtual
Dressing Room for Wheelchair-Bound Customers=978-1-4799-5158- 1/14/$31.00 ©2014
IEEE
[6] Masaki IZUTSU, and Shosiro HATAKEYAMA <Estimation Method of Clothes Size for
Virtual Fitting Room with Kinect Sensor= 978-1-4799-0652-9/13 $31.00 © 2013 IEEE
[7] OpenNI. http://www.openni.org/

[8] D. Chai, and K. N. Ngan, Face Segmentation using SkinColor Map in Videophone
Applications, IEEE Transactions on Circuits and Systems for Video Technology, vol. 9, no.
4, June 1999.
[9] Kinect Quick Start Guide, http://support.xbox.com/en- [10] Real time apparel
visualization By ShabbirMarzban Mohammad HarisBaig

Page 43