| Issue |
ITM Web Conf.
Volume 59, 2024
II International Workshop “Hybrid Methods of Modeling and Optimization in Complex Systems” (HMMOCS-II 2023)
|
|
|---|---|---|
| Article Number | 03011 | |
| Number of page(s) | 6 | |
| Section | Data Mining, Machine Learning and Patern Recognition | |
| DOI | https://doi.org/10.1051/itmconf/20245903011 | |
| Published online | 25 January 2024 | |
The automated recognition part markings algorithms
1
Togliatti State University, department « Equipment and Technologies of machine-building production »,
Togliatti City,
Russian Federation
2
Togliatti State University, department « Design and Operation of cars »,
Togliatti City,
Russian Federation
* Corresponding author: L.Ugarova@tltsu.ru
The development is aimed at the problem parts marking recognizing solving in mechanical engineering. Marking makes it possible to ensure the correct parts use and assemblies during assembly, to facilitate the assembly processes automation in production conditions. The algorithms and procedures presented in the article are based on a mathematical apparatus for improving the marking image quality and its recognition. The paper presents a functioning algorithm for the evaluation subsystem and improving the marking image quality based on the processing procedure “sliding window”. A marking recognition algorithm has been developed, the task of which is to recognize the symbols and designations that form the marking. The marking selection procedure result example on the object is given. The proposed algorithms allow for the product markings recognition in production conditions with sufficient reliability.
© The Authors, published by EDP Sciences, 2024
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.