Virtual Dressing Room Using OpenCv

Batch No:20CSEA013
Supervisor:
Mr K. Sandeep M.Tech
Associate Professor
Team Members : Computer Science and
M. Yamini    (17K61A05F0) Engineering
Ch. Jahnavi Naga (17K61A0517)
P. Girish Kumar (17K61A05F9)
S. Farookh   (17K61A05A5)
Contents
▪ INTRODUCTION
▪ METHODOLOGY
▪ MODULE DIVISION
▪ GANTT CHART
▪ ARCHITECTURE DIAGRAM
▪ DATA FLOW DIAGRAM
▪ ACTIVITY DIAGRAM
▪ USE CASE DIAGRAM
▪ PROPOSED SYSTEM
▪ SOFTWARE REQUIREMENTS
▪ HARDWARE REQUIREMENTS
▪ ALGORITHMS/TECHNIQUES USED
▪ PLAN OF ACTION
▪ EXPECTED OUTCOME
▪ REFERENCES
Abstract

With the advanced technology growth, online shopping as known as e-shopping has
grown exponentially throughout the world nowadays. Advances in e-shopping has
driven a shopping revolution where customers are able to purchase items anywhere and
anytime. Despite the benefits of e-shopping, the main drawback is the difficulty for
online shoppers to try items on especially for clothing. Hence, a virtual fitting room
using AR is proposed to be developed to allow shoppers to visualize how clothing looks
and fits on their bodies without wearing it actually. This is to improve shoppers’
shopping experience by giving them an ability to virtually try clothing on in order to
check for size, fit or style.
Methodology

❏ First of all for we need to detect body parts of target human body and we need to transfer
things according to suitable body parts.
❏ So for body part detection we were used haar cascade dataset.
❏ Using the cascade trainer gui value of feature is computed using concept of integral
images(it would select best value of feature among this by using adaboost classifier)
❏ They are like convolutional kernels. haar features are relavent feature for object detection
and non-relevant features are discarded by adaboost algorithm.
❏ Process of training haar cascade:
❏ •Haar feature(white black boxes moving on to the image and extract the feature.)
❏ •Integral images approach(to make fasten the process of computation of data)
❏ •Adaboost classifier (extract best feature and discarding non-relevant feature)
Module Division

1. Detecting and Sizing the Body

2. Face Detection
3. Image Masking
4. Edge Detection
5. Scaling of Attire
6. Proposed Application
Gantt chart
Architecture Diagram
Data Flow Diagram
Activity Diagram
Use Case Diagram
Proposed System

Working of
algorithm
Software Requirements

•Software Requirement:
•Cmake (3.12.0)
•Dlib (19.15.0)
•Opencv (3.4.2.17)
•Scipy (1.0.0)
•Cascade trainer gui (1.8.0)
•Tkinter canvas (8.6.8)
•Numpy (1.18.1)
•Anaconda (4.8.2)
•Python (3.7.4)
•Flask Web framework (1.1.1)
 Hardware Requirements
Laptop Requirements

System Type 32/64-bit Operating System

Processor Intel(R) Core(TM) i5-8750H CPU

@ 2.20GHz
Graphics Processor Intel(R) UHD Graphics 630

Graphics Card NVIDIA GeForce GTX 1050

RAM 8.0 GB DDR4 2666MHz

Operating System Microsoft Windows 10

 Algorithm
Step1: Use of OpenCv
Step2: Capturing the video using openCv packages (cv2)
Step3:OpenCV uses color contrast based differentiation of objects by detecting the pixels which
reside on the boundaries where colors change values significantly.
Step4:Haar classifier contains a various function which together helps in detecting the different
objects in a frame
Step5:Augmentation of colours and logos -. Here in our case, we want the outermost containing
contour which will relate to the dress which the user or test object is wearing
Step6 :With Integral images approach impose the clothes and ornaments to human body
Step7:It makes the process user interactions with the help of Numpy/OpenCV packages for
edge detection,Scaling of attire and Context Embedding.
Plan of Action
Expected Outcome

In the proposed system, we will describe a simple and efficient Trial Room with virtual
usage. This application helps the user to visualize his/her own attire without actually
wearing it. Initially the user needs to face the camera which focuses the user image and fit
various costumes to it and displays. This basically helps the user to know his/her choice
easily and provide greater level of satisfaction.
References
❏ [1]Amit Thakur1,Suraj Virkar2,Prof.Jyoti Gaikwad,"Online Virtual Trial Room Implementation using OpenCV Python",
Volume:07 Issue:05|May 2020

❏ [2]Saurabh Botre1, Sushant Chaudhari2, Shamla Mantri3,"Virtual Trial Room",Volume 2 Issue 2, Mar-Apr 2014

❏ [3]Zambare Triveni V, Keskar Ankita D, Shinde Prajakta S, Deo Juilee V, Prof.Ratnaraj Kumar, “Virtual Dressing View”,
Volume No:07, Issue:03 April 2018.

❏ [4]Nikki Singh, Sagar Murade, Prem Lone, Vikas Mulaje, "Virtual Trial Room”, Volume No: 1, Issue:04,December 2017

❏ [5]Zhonghua Wu, Guosheng Lin, Qingyi Tao, Jianfei Cai,‘M2E-Try On Net: Fashion from Model to Everyone’, Pages 293–
301,in2019

❏ [6]Ting Liu; LingZhi Li; XiWen Zhang,‘Real-time 3D virtual dressing based on users' skeletons’,11-13 Nov. 2017.

❏ [7]Ari Kusumaningsihand EkoMulyantoYuniarno, “User Experience Measurement On Virtual Dressing Room Of Madura
Batik Clothes”, IEEE2017

❏ [8]Srinivasan K. and Vivek S., “Implementation Of Virtual Fitting Room Using Image Processing” IEEE2017.
THANK YOU