• Version
• Download 21
• File Size 295.62 KB
• File Count 1
• Create Date 11 May 2023
• Last Updated 11 May 2023

VIRTUAL TOP-TRY-ON USING DEEP LEARNING

VIRTUAL TOP-TRY-ON USING DEEP LEARNING

Dr.P.D.R.Vijayakumar,M.E.,Ph.D., P.Gokila,M.E., B.Durgadevi, S.Srikanth, CB.Veerakumar, S.Yogapriya.

Dr.P.D.R.Vijayakumar HOD-CSE & INFO INSTITUTE OF ENGINEERING, COIMBATORE

P.Gokila AP- CSE & INFO INSTITUTE OF ENGINEERING, COIMBATORE

B.DurgaDevi BE CSE & INFO INSTITUTE OF ENGINEERING, COIMBATORE

S.Srikanth BE CSE & INFO INSTITUTE OF ENGINEERING, COIMBATORE

CB.Veerakumar BE CSE & INFO INSTITUTE OF ENGINEERING, COIMBATORE

S.Yogapriya BE CSE & INFO INSTITUTE OF ENGINEERING, COIMBATORE

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - The evaluation mainly focuses on dealing with virtual try-on. With the rapid development of image classification, there is a profound growth of garment purchases through the internet. We can fit or suggest the appropriate top to corresponding input frontal women image by using classification algorithm fit evaluation of virtual women top try-on is vital in the clothing industry. Image dataset (Frontal women and top images) is implemented as input. We propose a Convolutional Neural Network model to evaluate perfect outfit. The inputs of the proposed model are digital clothing pressures of different Frontal women and top images, while the output is the predicted result of Frontal women and top fit or unfit. Virtual Try-On new VR technologies have been developed, which form the basis for a realistic, three dimensional, simulation and visualization of individualized garments put on by virtual counterparts of real customers. To provide this cloning and dressing of people in VR, a complete process chain is being build up starting with the touch- less 3-dimensional scanning of the human body up to a photo-realistic 3-dimensional presentation of the virtual customer dressed in the chosen pieces of clothing. The emerging platform for interactive selection and configuration of virtual garments, the "virtual shop", will be accessible in real fashion boutiques as well as over the internet, thereby supplementing the conventional distribution channels.

Key Words:  VITON, Deep learning, Python, Image classification, Neural networks, CNN