Bangladeshi Traditional Virtual Try-On with Deep Learning Techniques and Computer Vision

Date
2023
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
With a growing trend toward online shopping, virtually wearing clothes can enrich a customer’s experience, as it gives an idea about how different outfits would appear on them. Virtual try-on is similar to image synthesis but has unique and challenging aspects that can be revolutionary in the shopping world. We present a smart system where a user can search for clothes without going to a store and can virtually try outfits instead of dealing with unsafe trial rooms. From this, it is possible to see how the user will look in the desired outfit. This virtual experience can make it easier and more convenient for people of different ages to try on multiple clothes. The system will place and render a cloth onto the user image to generate an output by blending the outfit with the real image using deep learning techniques and computer vision. We are the first one to introduce the system to Bangladeshi traditional outfits. We believe that it will create a virtual outfit try-on environment in our country.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN