| Title |
Polietileno tereftalato (PET) taros ruošinio defektų aptikimo metodų sukūrimas ir tyrimas / |
| Translation of Title |
Development and analysis of polyethylene terephthalate (PET) preform defect detection methods. |
| Authors |
Kairys, Lukas |
| Full Text |
|
| Pages |
55 |
| Keywords [eng] |
PET ; defect detection ; computer vision ; quality control |
| Abstract [eng] |
The aim of this paper is to create a method for detecting structural defets of PET preforms using polarized light filters, and investigate its effectivness comparing different system configurations. In the first part of paper scientific articles of indurstrial quality control control methods and defect detection systems are reviewed, as well as the computer vision applications in industry. In the second part of paper theoretical background of used image processing filters, image feature descriptors and machine learning classifiers are presented. In the third part of paper the used experimental equipment is described, the research of suggested methods is performed and the results analized. In the final part of paper conclusions and recomendations are presented. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2016 |
