Flaw Detection from Ultrasonic Images using YOLO and SSD

Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space industry. Due to a vast amount of time needed for a human expert to perform inspection it is practical for a computer to take over that task. Some...

Full description

Saved in:
Bibliographic Details
Published in:2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) pp. 163 - 168
Main Authors: Posilovic, Luka, Medak, Duje, Subasic, Marko, Petkovic, Tomislav, Budimir, Marko, Loncaric, Sven
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2019
Subjects:
Acoustics
automated flaw detection
Computer architecture
convolutional neural networks
Discrete wavelet transforms
image analysis
image processing
Inspection
non-destructive testing
Probes
Testing
Training
ultrasonic imaging
ISSN:1849-2266
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space industry. Due to a vast amount of time needed for a human expert to perform inspection it is practical for a computer to take over that task. Some attempts have been made to produce algorithms for automatic UT scan inspection mainly using older, non-flexible analysis methods. In this paper, two deep learning based methods for flaw detection are presented, YOLO and SSD convolutional neural networks. The methods' performance was tested on a dataset that was acquired by scanning metal blocks containing different types of defects. YOLO achieved average precision (AP) of 89.7% while SSD achieved AP of 84.5 %.
AbstractList Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space industry. Due to a vast amount of time needed for a human expert to perform inspection it is practical for a computer to take over that task. Some attempts have been made to produce algorithms for automatic UT scan inspection mainly using older, non-flexible analysis methods. In this paper, two deep learning based methods for flaw detection are presented, YOLO and SSD convolutional neural networks. The methods' performance was tested on a dataset that was acquired by scanning metal blocks containing different types of defects. YOLO achieved average precision (AP) of 89.7% while SSD achieved AP of 84.5 %.
Author Posilovic, Luka
Medak, Duje
Loncaric, Sven
Subasic, Marko
Budimir, Marko
Petkovic, Tomislav
Author_xml – sequence: 1
  givenname: Luka
  surname: Posilovic
  fullname: Posilovic, Luka
  email: luka.posilovic@fer.hr
  organization: Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
– sequence: 2
  givenname: Duje
  surname: Medak
  fullname: Medak, Duje
  email: duje.medak@fer.hr
  organization: Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
– sequence: 3
  givenname: Marko
  surname: Subasic
  fullname: Subasic, Marko
  organization: Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
– sequence: 4
  givenname: Tomislav
  surname: Petkovic
  fullname: Petkovic, Tomislav
  organization: Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
– sequence: 5
  givenname: Marko
  surname: Budimir
  fullname: Budimir, Marko
  organization: INETEC Institute for Nuclear Technology, Dolenica, Croatia
– sequence: 6
  givenname: Sven
  surname: Loncaric
  fullname: Loncaric, Sven
  organization: Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
BookMark eNotz8tKw0AYQOFRFKw1DyBu5gUS535ZltZqIBAhduGqTGb-lIFmIpmI-PYu7OrsPjj36CZNCRB6pKSilNjnunvfVIxQWxmjjGX2ChVWG6qZoZwKIq_RihphS8aUukNFzrEnwkgitDUrZPZn94N3sIBf4pTwME8jPpyX2eUpRY_r0Z0g4-8c0wl_tk2LXQq463YP6HZw5wzFpWt02L98bN_Kpn2tt5umjIzwpXQqEE80s-B6oYJmRASuQQkNQWqnCWg-COU8BzbwnugQglRBST8YLyXja_T070YAOH7NcXTz7_Hyyv8ATVlIbA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ISPA.2019.8868929
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781728131405
1728131405
EISSN 1849-2266
EndPage 168
ExternalDocumentID 8868929
Genre orig-research
GroupedDBID 6IE
6IL
ABLEC
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IEGSK
RIE
RIL
ID FETCH-LOGICAL-i203t-a6d0c0729eab46d7204d37e647ed57a70e73f46ac3e2f3b07ddd56d65cf8c5523
IEDL.DBID RIE
ISICitedReferencesCount 37
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000865974800029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Jun 26 19:27:11 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-a6d0c0729eab46d7204d37e647ed57a70e73f46ac3e2f3b07ddd56d65cf8c5523
PageCount 6
ParticipantIDs ieee_primary_8868929
PublicationCentury 2000
PublicationDate 2019-Sept.
PublicationDateYYYYMMDD 2019-09-01
PublicationDate_xml – month: 09
  year: 2019
  text: 2019-Sept.
PublicationDecade 2010
PublicationTitle 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA)
PublicationTitleAbbrev ISPA
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib048504798
ssib042470063
Score 1.9498943
Snippet Non-destructive ultrasonic testing (UT) of materials is used for monitoring critical parts in power plants, aeronautics, oil and gas industry, and space...
SourceID ieee
SourceType Publisher
StartPage 163
SubjectTerms Acoustics
automated flaw detection
Computer architecture
convolutional neural networks
Discrete wavelet transforms
image analysis
image processing
Inspection
non-destructive testing
Probes
Testing
Training
ultrasonic imaging
Title Flaw Detection from Ultrasonic Images using YOLO and SSD
URI https://ieeexplore.ieee.org/document/8868929
WOSCitedRecordID wos000865974800029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5t8eBJpRXf5ODRtelm89ijWIsFaQu1UE8lycxKoW6lu9W_b7KtFcGLtySEkElCvkzmmxlCrm3HZdhBHimwIvIv4izyuB5HHlks19pa4VyVbEINBno6TUc1crPzhUHEinyGt6FY2fJh6dbhq6yttdQezuukrpTc-Gp9n50kTlSA211dixA8XW8NmR2Wtvvj0V3gcoXDUY3zK6FKhSe9g__N5JC0fhzz6GgHOUekhnmT6N7CfNIulhWrKqfBY4ROFuXKFCHuLe2_-TujoIHh_kpfhk9DanKg43G3RSa9h-f7x2ibECGax4yXkZHAXAj1jcYmEkJ-GeAKZaIQhDKKoeJZIo3jGGfcMgUAQoIULtNOeJXzmDTyZY4nhBrhfH9r0RivHKdgOIOEW-H7MYA0PSXNIPXsfRPzYrYV-Ozv5nOyHxZ2w726II1ytcZLsuc-ynmxuqo26gv7YpMV
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4QTfSkBoxve_DoStk-92hUAhGBBEjwRPqYNSS4GFj079suiDHx4q1tmqbTNv06nW9mELo2dZtCHWgkneGRfxGnkcf1OPLIYqhSxnBri2QTstNRo1HSK6GbjS8MABTkM7gNxcKW72Z2Gb7KakoJ5eF8C21zxmKy8tb6Pj0sZjIA7qaueAifrtamzDpJaq1-7y6wucLxKEb6lVKlQJTG_v_mcoCqP655uLcBnUNUgqyCVGOqP_ED5AWvKsPBZwQPp_lcL0LkW9x687fGAgeO-yt-6ba7WGcO9_sPVTRsPA7um9E6JUI0iQnNIy0csSHYN2jDhAsZZhyVIJgEx6WWBCRNmdCWQpxSQ6RzjgsnuE2V5V7pPELlbJbBMcKaW9_fGNDaq8eJ05Q4Rg33_YhzSXKCKkHq8fsq6sV4LfDp381XaLc5eG6P263O0xnaC4u8YmKdo3I-X8IF2rEf-WQxvyw27QvVn5Zc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2019+11th+International+Symposium+on+Image+and+Signal+Processing+and+Analysis+%28ISPA%29&rft.atitle=Flaw+Detection+from+Ultrasonic+Images+using+YOLO+and+SSD&rft.au=Posilovic%2C+Luka&rft.au=Medak%2C+Duje&rft.au=Subasic%2C+Marko&rft.au=Petkovic%2C+Tomislav&rft.date=2019-09-01&rft.pub=IEEE&rft.eissn=1849-2266&rft.spage=163&rft.epage=168&rft_id=info:doi/10.1109%2FISPA.2019.8868929&rft.externalDocID=8868929