Issue |
E3S Web Conf.
Volume 304, 2021
2nd International Conference on Energetics, Civil and Agricultural Engineering (ICECAE 2021)
|
|
---|---|---|
Article Number | 02013 | |
Number of page(s) | 5 | |
Section | Civil Engineering | |
DOI | https://doi.org/10.1051/e3sconf/202130402013 | |
Published online | 02 December 2021 |
Study on signs of defects in the image of the surface of flat-rolled products
1 Magnitogorsk State Technical University named after G. I. Nosov, 455000 Magnitogorsk, Russia
2 Tashkent Institute of Irrigation and Agricultural Mechanization Engineers, 100000 Tashkent, Uzbekistan
3 Tashkent State Technical University, 100095 Tashkent, Uzbekistan
* Corresponding author: evgenyjam@yandex.ru
Currently, more and more challenges of modern industrial enterprises require an increase in the reliability of the information on the quality of products. This becomes possible when using digital technologies to assess the quality of products. The cited publication discusses the technology for recognizing defects in the surface of sheet products in images obtained from cameras of the strip inspection system during rolling. The authors proposed a classification of the signs of defects in the image and highlighted the most significant of them also suggested using geometric, optical and spectral features for images of flat-rolled products containing defects of different classes. The research results at this stage, obtained during the processing of digital images, showed that to identify a defect and reduce false-positive and false-negative alarms of the automated defect identification system, it is required to conduct a study of interval estimates and make decision-making rules based on intersection and merging of intervals; introduce additional classes that allow the introduction of signs that characterize the irregularity of the shape of defects and the characteristic location; the use of new technologies of soft computing will reveal the hidden patterns of the manifestation of defects in the images of the surface of the steel strip.
© The Authors, published by EDP Sciences, 2021
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.