No Cover Image

Conference Paper/Proceeding/Abstract 517 views 23 downloads

A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction

Mahmoud Salem Orcid Logo, Ahmed Elkaseer Orcid Logo, Andrew Rees, Steffen Scholz

Proceedings of the Future Technologies Conference (FTC) 2022, Volume: 2, Pages: 848 - 861

Swansea University Authors: Andrew Rees, Steffen Scholz

Check full text

DOI (Published version): 10.1007/978-3-031-18458-1_58

Abstract

Reverse engineering (RE) has played a key role in producing low demands parts, especially with the recent advent of robust additive manufacturing (AM) techniques. The synergetic interaction of both cutting-edge RE and AM techniques significantly enhance part re-producing and minimize the product dev...

Full description

Published in: Proceedings of the Future Technologies Conference (FTC) 2022
ISBN: 9783031184574 9783031184581
ISSN: 2367-3370 2367-3389
Published: Cham Springer International Publishing 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62064
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-11-28T10:22:18Z
last_indexed 2023-01-13T19:23:16Z
id cronfa62064
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>62064</id><entry>2022-11-28</entry><title>A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction</title><swanseaauthors><author><sid>e43e88c74976e714e1d669a898f8470d</sid><ORCID/><firstname>Andrew</firstname><surname>Rees</surname><name>Andrew Rees</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>20c4a48c9bf558852c28f1640e01ef50</sid><firstname>Steffen</firstname><surname>Scholz</surname><name>Steffen Scholz</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-11-28</date><deptcode>ACEM</deptcode><abstract>Reverse engineering (RE) has played a key role in producing low demands parts, especially with the recent advent of robust additive manufacturing (AM) techniques. The synergetic interaction of both cutting-edge RE and AM techniques significantly enhance part re-producing and minimize the product development cycle time, even if there is no blueprint for the desired product. Recently, computer vision algorithms have enhanced the RE process and strengthen its capabilities to reconstruct challenging shapes. Nevertheless, the large body of the reported literature is restricted to estimate the 3D shape of the scanned part from a single/multiple 2D/3D image based on predefined classes using supervised learning. The ability to reconstruct intricate geometrical features of real mechanical parts and complex shapes has not been fully realized yet. In this context, this paper reports on a hybrid learning technique-based conceptual computer vision framework to enhance RE process for reproducing of low demand products. The hybrid learning proposed herein is a supervised and unsupervised learning technique using a dual deep learning models to enrich the computer vision technique with the ability to reconstruct 3D complex features using a single 3D depth image.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the Future Technologies Conference (FTC) 2022</journal><volume>2</volume><journalNumber/><paginationStart>848</paginationStart><paginationEnd>861</paginationEnd><publisher>Springer International Publishing</publisher><placeOfPublication>Cham</placeOfPublication><isbnPrint>9783031184574</isbnPrint><isbnElectronic>9783031184581</isbnElectronic><issnPrint>2367-3370</issnPrint><issnElectronic>2367-3389</issnElectronic><keywords>Computer Vision, Machine Learning, Deep Learning, Hybrid learning, 3D Reconstruction, Production, Additive Manufacturing (AM), Reverse Engineering (RE)</keywords><publishedDay>13</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-10-13</publishedDate><doi>10.1007/978-3-031-18458-1_58</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2024-07-29T15:59:10.7387954</lastEdited><Created>2022-11-28T10:19:46.5995266</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Mahmoud</firstname><surname>Salem</surname><orcid>0000-0003-2459-0271</orcid><order>1</order></author><author><firstname>Ahmed</firstname><surname>Elkaseer</surname><orcid>0000-0002-2500-3617</orcid><order>2</order></author><author><firstname>Andrew</firstname><surname>Rees</surname><orcid/><order>3</order></author><author><firstname>Steffen</firstname><surname>Scholz</surname><order>4</order></author></authors><documents><document><filename>62064__25926__f6fc05b5f489462594ddf70f0d0f47c0.pdf</filename><originalFilename>Salem_et_al_PaperCameraReady AE07 (2).pdf</originalFilename><uploaded>2022-11-28T11:15:29.4326636</uploaded><type>Output</type><contentLength>960881</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2023-10-13T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling v2 62064 2022-11-28 A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction e43e88c74976e714e1d669a898f8470d Andrew Rees Andrew Rees true false 20c4a48c9bf558852c28f1640e01ef50 Steffen Scholz Steffen Scholz true false 2022-11-28 ACEM Reverse engineering (RE) has played a key role in producing low demands parts, especially with the recent advent of robust additive manufacturing (AM) techniques. The synergetic interaction of both cutting-edge RE and AM techniques significantly enhance part re-producing and minimize the product development cycle time, even if there is no blueprint for the desired product. Recently, computer vision algorithms have enhanced the RE process and strengthen its capabilities to reconstruct challenging shapes. Nevertheless, the large body of the reported literature is restricted to estimate the 3D shape of the scanned part from a single/multiple 2D/3D image based on predefined classes using supervised learning. The ability to reconstruct intricate geometrical features of real mechanical parts and complex shapes has not been fully realized yet. In this context, this paper reports on a hybrid learning technique-based conceptual computer vision framework to enhance RE process for reproducing of low demand products. The hybrid learning proposed herein is a supervised and unsupervised learning technique using a dual deep learning models to enrich the computer vision technique with the ability to reconstruct 3D complex features using a single 3D depth image. Conference Paper/Proceeding/Abstract Proceedings of the Future Technologies Conference (FTC) 2022 2 848 861 Springer International Publishing Cham 9783031184574 9783031184581 2367-3370 2367-3389 Computer Vision, Machine Learning, Deep Learning, Hybrid learning, 3D Reconstruction, Production, Additive Manufacturing (AM), Reverse Engineering (RE) 13 10 2022 2022-10-13 10.1007/978-3-031-18458-1_58 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University 2024-07-29T15:59:10.7387954 2022-11-28T10:19:46.5995266 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Mahmoud Salem 0000-0003-2459-0271 1 Ahmed Elkaseer 0000-0002-2500-3617 2 Andrew Rees 3 Steffen Scholz 4 62064__25926__f6fc05b5f489462594ddf70f0d0f47c0.pdf Salem_et_al_PaperCameraReady AE07 (2).pdf 2022-11-28T11:15:29.4326636 Output 960881 application/pdf Accepted Manuscript true 2023-10-13T00:00:00.0000000 true eng
title A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
spellingShingle A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
Andrew Rees
Steffen Scholz
title_short A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
title_full A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
title_fullStr A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
title_full_unstemmed A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
title_sort A Hybrid Learning-Driven Computer Vision Framework for Reverse Engineering via Enhanced 3D Shape Reconstruction
author_id_str_mv e43e88c74976e714e1d669a898f8470d
20c4a48c9bf558852c28f1640e01ef50
author_id_fullname_str_mv e43e88c74976e714e1d669a898f8470d_***_Andrew Rees
20c4a48c9bf558852c28f1640e01ef50_***_Steffen Scholz
author Andrew Rees
Steffen Scholz
author2 Mahmoud Salem
Ahmed Elkaseer
Andrew Rees
Steffen Scholz
format Conference Paper/Proceeding/Abstract
container_title Proceedings of the Future Technologies Conference (FTC) 2022
container_volume 2
container_start_page 848
publishDate 2022
institution Swansea University
isbn 9783031184574
9783031184581
issn 2367-3370
2367-3389
doi_str_mv 10.1007/978-3-031-18458-1_58
publisher Springer International Publishing
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 1
active_str 0
description Reverse engineering (RE) has played a key role in producing low demands parts, especially with the recent advent of robust additive manufacturing (AM) techniques. The synergetic interaction of both cutting-edge RE and AM techniques significantly enhance part re-producing and minimize the product development cycle time, even if there is no blueprint for the desired product. Recently, computer vision algorithms have enhanced the RE process and strengthen its capabilities to reconstruct challenging shapes. Nevertheless, the large body of the reported literature is restricted to estimate the 3D shape of the scanned part from a single/multiple 2D/3D image based on predefined classes using supervised learning. The ability to reconstruct intricate geometrical features of real mechanical parts and complex shapes has not been fully realized yet. In this context, this paper reports on a hybrid learning technique-based conceptual computer vision framework to enhance RE process for reproducing of low demand products. The hybrid learning proposed herein is a supervised and unsupervised learning technique using a dual deep learning models to enrich the computer vision technique with the ability to reconstruct 3D complex features using a single 3D depth image.
published_date 2022-10-13T15:59:09Z
_version_ 1805925901303545856
score 11.035765

Similar Items