Automatic body measurement by neural networks
Size prediction and garment customization are two main goals of body measurement for garment design. Traditional body measurement, involving manual measurement and trying clothes in person, is time-consuming and not cost-efficient. With the help of 3D body scanner and neural networks, body measureme...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/77220 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-77220 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-772202023-03-03T20:39:18Z Automatic body measurement by neural networks Zhao, Jingyi Qian Kemao School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling Size prediction and garment customization are two main goals of body measurement for garment design. Traditional body measurement, involving manual measurement and trying clothes in person, is time-consuming and not cost-efficient. With the help of 3D body scanner and neural networks, body measurement can be fast and precise, thus reducing the cost. This project introduces neural network models to predict body sizes and the measurements used to customize clothes from various body data. In this project, three kinds of input data are used: raw 3D point clouds of human bodies, key body locations, and estimated body measurements. Raw point clouds are collected by scanning the participants’ body, and key body locations and estimated measurements are automatically computed by existing software. Then the manual measurement is applied to the participants to obtain the size labels and useful measurements for garment customization, which are used as the ground-truth values of output data. Different network structures are utilized for different kinds of input data. The results show that neural networks can achieve decent performance in predicting measurements for making clothes, and different input data can lead to different accuracies of prediction. The models can be further improved with a larger amount of data, in order to make it production-ready. Bachelor of Engineering (Computer Science) 2019-05-17T07:51:16Z 2019-05-17T07:51:16Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77220 en Nanyang Technological University 34 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling |
spellingShingle |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling Zhao, Jingyi Automatic body measurement by neural networks |
description |
Size prediction and garment customization are two main goals of body measurement for garment design. Traditional body measurement, involving manual measurement and trying clothes in person, is time-consuming and not cost-efficient. With the help of 3D body scanner and neural networks, body measurement can be fast and precise, thus reducing the cost. This project introduces neural network models to predict body sizes and the measurements used to customize clothes from various body data. In this project, three kinds of input data are used: raw 3D point clouds of human bodies, key body locations, and estimated body measurements. Raw point clouds are collected by scanning the participants’ body, and key body locations and estimated measurements are automatically computed by existing software. Then the manual measurement is applied to the participants to obtain the size labels and useful measurements for garment customization, which are used as the ground-truth values of output data. Different network structures are utilized for different kinds of input data. The results show that neural networks can achieve decent performance in predicting measurements for making clothes, and different input data can lead to different accuracies of prediction. The models can be further improved with a larger amount of data, in order to make it production-ready. |
author2 |
Qian Kemao |
author_facet |
Qian Kemao Zhao, Jingyi |
format |
Final Year Project |
author |
Zhao, Jingyi |
author_sort |
Zhao, Jingyi |
title |
Automatic body measurement by neural networks |
title_short |
Automatic body measurement by neural networks |
title_full |
Automatic body measurement by neural networks |
title_fullStr |
Automatic body measurement by neural networks |
title_full_unstemmed |
Automatic body measurement by neural networks |
title_sort |
automatic body measurement by neural networks |
publishDate |
2019 |
url |
http://hdl.handle.net/10356/77220 |
_version_ |
1759854952231993344 |