Szczegóły publikacji
Opis bibliograficzny
Computer-aided detection of defects in the investment casting / PUCHLERSKA Sandra, ŻABA Krzysztof, Pyzik Jarosław // W: METAL 2018 : 27th international conference on Metallurgy and materials : May 23rd – 25th 2018, Brno, Czech Republic : abstracts. — Ostrava : TANGER Ltd., cop. 2018. — ISBN: 978-80-87294-83-3. — S. 97. — Pełny tekst W: METAL 2018 [Dokument elektroniczny] : 27th international conference on Metallurgy and materials : May 23rd–25th 2018, Brno : conference proceedings : reviewed version. — Dane tekstowe. – Wersja do Windows. — Ostrava : TANGER Ltd., cop. 2018. — 1 dysk optyczny — S. 181–185. — Wymagania systemowe: Adobe Reader ; napęd CD-ROM. — Bibliogr. s. 185, Abstr. — ISBN 978-80-87294-84-0. — W pełnym tekście kolejność nazwisk autorów: K. Żaba, S. Puchlerska, J. Pyzik
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 114094 |
|---|---|
| Data dodania do BaDAP | 2018-06-07 |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | 27th international conference on Metallurgy and materials |
Abstract
Computer-aided image recognition methods are non-invasive, easy to implement and quick to calculate defects detection methods. They seem to be a promising method for investment casting applications - defects can be detected in individual incestment casting processes, reducing the costs caused by defective castings. As part of the research, defects have been defined and described in wax models. For each of the disadvantages, a characteristic signature was created allowing for its later detection in the image. In the next stage pre-processing of models was carried out, including segmentation, denoising and sharpening in order to prepare images for the input form for the algorithm. Next, an algorithm for searching and classifying areas containing separate defects and deviations from correct images was developed. The algorithm uses statistical classification methods and machine learning elements using convolutional neural networks. © 2018 TANGER Ltd., Ostrava.
