hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Automatic quality assessment of formed fiber products via Computer Vision and Artificial Intelligence
Halmstad University, School of Information Technology. SE991228719101.
2023 (English)Independent thesis Basic level (professional degree), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Defects on fiber products have varied appearances and are common in production lines. A reliable system that can classify and identify defects without subjectivity and fatigue can improve a company's quality management. Computer vision systems are crucial for any autonomous system, but accuracy is essential for real-life applications. This study aims to investigate the contribution of computer vision through computer vision and artificial intelligence in detecting defects in formed fiber products. A hand-crafted dataset of four common defects from the production line was created and tested using transfer learning. The system's performance was measured in terms of mean average precision (mAP), precision, and recall, resulting in a performance of 81.8% mAP, 0.84 recall rate, and 0.79 precision rate for the hand-crafted dataset.

Abstract [sv]

Defekter på fiberprodukter har olika framträdanden och är vanliga i produktionslinjer. Ett tillförlitligt system som kan klassificera och identifiera defekter utan subjektivitet och trötthet kan förbättra ett företags kvalitetsledning. Ett datorseende-system är avgörande för alla autonoma system, men noggrannhet är viktigt för tillämpningar i verkliga livet. Denna studie syftar till att undersöka bidraget från datorseende genom datorseende och artificiell intelligens för att upptäcka defekter i formade fiberprodukter. Ett handgjort dataset med fyra vanliga defekter från produktionslinjen skapades och testades med transfer learning. Systemets prestanda mättes i termer av medelvärde av genomsnittlig precision (mAP), precision och återkallelse, vilket resulterade i en prestanda på 81,8% mAP, 0,84 återkallningsfrekvens och 0,79 precision frekvens för det handgjorda datasetet.  

Place, publisher, year, edition, pages
2023. , p. 53
Keywords [en]
Artificial intelligence, Deep learning, CNN, YOLO, Computer Vision, Fiber products, Machine learning, Neural network
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:hh:diva-50376OAI: oai:DiVA.org:hh-50376DiVA, id: diva2:1752802
External cooperation
Stora Enso Hyltebruk
Educational program
Mechatronic Engineer, 180 credits
Supervisors
Examiners
Available from: 2023-05-08 Created: 2023-04-24 Last updated: 2023-05-08Bibliographically approved

Open Access in DiVA

fulltext(1195 kB)291 downloads
File information
File name FULLTEXT02.pdfFile size 1195 kBChecksum SHA-512
3d280f519f3f8db885b1a17634a664595af0be577155a7bab384b724a1fa7c5616844c82047881cb62efb3364647ff692f5ce1d81b7eae40472be0db5b0794ab
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Sköld, Jesper
By organisation
School of Information Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 291 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 594 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf