Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision
This paper discusses the possibilities of an automated solution for determining dimensionally accurate and defective products using a computer vision system. In a real industrial environment, research was conducted on a prototype of a quality control machine, i.e. a machine that, based on product im...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
University North
2023-01-01
|
Series: | Tehnički Glasnik |
Subjects: | |
Online Access: | https://hrcak.srce.hr/file/423367 |
_version_ | 1797206627831513088 |
---|---|
author | Ilija Svalina Dražen Turinski Ivan Grgić Sara Havrlišan |
author_facet | Ilija Svalina Dražen Turinski Ivan Grgić Sara Havrlišan |
author_sort | Ilija Svalina |
collection | DOAJ |
description | This paper discusses the possibilities of an automated solution for determining dimensionally accurate and defective products using a computer vision system. In a real industrial environment, research was conducted on a prototype of a quality control machine, i.e. a machine that, based on product images, evaluates whether the product is accurate or defective using computer vision. Various geometric features are extracted from the obtained images of products, on the basis of which a fuzzy inference system based on Fuzzy C-means clustering features is created. The extracted geometric features represent the input variables, and the output variable has two values - true and false. The root mean square error in the evaluation of the accuracy and defectiveness of products ranges between 0.07 and 0.16. Through this research, valuable findings and conclusions were reached for the future research, since this topic is poorly examined in the most renowned databases. |
first_indexed | 2024-04-24T09:10:02Z |
format | Article |
id | doaj.art-fe994c4c04d9453b80b1acd88799f63e |
institution | Directory Open Access Journal |
issn | 1846-6168 1848-5588 |
language | English |
last_indexed | 2024-04-24T09:10:02Z |
publishDate | 2023-01-01 |
publisher | University North |
record_format | Article |
series | Tehnički Glasnik |
spelling | doaj.art-fe994c4c04d9453b80b1acd88799f63e2024-04-15T18:16:21ZengUniversity NorthTehnički Glasnik1846-61681848-55882023-01-0117111211910.31803/tg-20221109143423Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer VisionIlija Svalina0Dražen Turinski1Ivan Grgić2Sara Havrlišan3University of Slavonski Brod, Mechanical Engineering Faculty in Slavonski Brod, Trg I. B. Mažuranić 2, 35000 Slavonski Brod, CroatiaUniversity of Slavonski Brod, Mechanical Engineering Faculty in Slavonski Brod, Trg I. B. Mažuranić 2, 35000 Slavonski Brod, CroatiaUniversity of Slavonski Brod, Mechanical Engineering Faculty in Slavonski Brod, Trg I. B. Mažuranić 2, 35000 Slavonski Brod, CroatiaUniversity of Slavonski Brod, Mechanical Engineering Faculty in Slavonski Brod, Trg I. B. Mažuranić 2, 35000 Slavonski Brod, CroatiaThis paper discusses the possibilities of an automated solution for determining dimensionally accurate and defective products using a computer vision system. In a real industrial environment, research was conducted on a prototype of a quality control machine, i.e. a machine that, based on product images, evaluates whether the product is accurate or defective using computer vision. Various geometric features are extracted from the obtained images of products, on the basis of which a fuzzy inference system based on Fuzzy C-means clustering features is created. The extracted geometric features represent the input variables, and the output variable has two values - true and false. The root mean square error in the evaluation of the accuracy and defectiveness of products ranges between 0.07 and 0.16. Through this research, valuable findings and conclusions were reached for the future research, since this topic is poorly examined in the most renowned databases.https://hrcak.srce.hr/file/423367computer visiondimensional controlfuzzy C-means clusteringimage processingvision measurement |
spellingShingle | Ilija Svalina Dražen Turinski Ivan Grgić Sara Havrlišan Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision Tehnički Glasnik computer vision dimensional control fuzzy C-means clustering image processing vision measurement |
title | Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision |
title_full | Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision |
title_fullStr | Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision |
title_full_unstemmed | Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision |
title_short | Possibilities of Evaluating the Dimensional Acceptability of Workpieces Using Computer Vision |
title_sort | possibilities of evaluating the dimensional acceptability of workpieces using computer vision |
topic | computer vision dimensional control fuzzy C-means clustering image processing vision measurement |
url | https://hrcak.srce.hr/file/423367 |
work_keys_str_mv | AT ilijasvalina possibilitiesofevaluatingthedimensionalacceptabilityofworkpiecesusingcomputervision AT drazenturinski possibilitiesofevaluatingthedimensionalacceptabilityofworkpiecesusingcomputervision AT ivangrgic possibilitiesofevaluatingthedimensionalacceptabilityofworkpiecesusingcomputervision AT sarahavrlisan possibilitiesofevaluatingthedimensionalacceptabilityofworkpiecesusingcomputervision |