Optimization of the calibration algorithm for laser marking systems equipped with computer vision

Cover Page


Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

BACKGROUND: Laser marking technology, based on the interaction of laser radiation with a substance for applying detailed images and inscriptions to various surfaces, is specified by excellent image reproduction accuracy, low power consumption and high processing rate compared to conventional methods.

Effective control of laser marking requires accurate calibration and tuning of the laser system to match surface material characteristics of treated objects. The most promising solution is introducing computer vision systems, enabling high accuracy, speed and scalability for implementation in modern production. Computer vision systems application in laser marking for quality and object orientation monitoring remains underdeveloped. This paper presents computer vision systems integration into a laser marking device through the SharpMark marker tuning algorithm.

AIM: Development of the software algorithm integrated with the computer vision system to automate the process of setting up the SharpMark laser facility for chasing and marking. The tasks solved in this study are aimed at improving image quality by optimizing the algorithm for tuning the laser system.

METHODS: The OpenCV computer vision library was used as the basis for the development of the computer vision system. The ArUco marks were used for accurate identification of the position of the marking object and calibration of the laser marker. The proposed algorithm is implemented in several sequential stages, including: detection of objects in the image, correction of image distortion (Undistort), perspective transformation (WarpPerspective) to compensate for distortions, contour extraction (FindContours) and widening of areas of interest (InflatePaths). The laser system is controlled by means of exchange of data and control commands.

RESULTS: The algorithm that determines object positions automatically and corrects contours for lens distortion by improving camera calibration accuracy has been developed. The calibration method, which defines the camera’s pixel-to-millimeter ratio, enables image linking to marker coordinates for precise marking with an accuracy of up to 0.1mm over a 10 cm distance. The algorithm automatically marks multiple objects within the working area.

CONCLUSION: The practical value of this study lies in enhancing SharpMark’s efficiency by means of optimization of the calibration algorithm. The proposed algorithm is applicable to similar computer vision-equipped laser marking systems and to any automated pattern recognition systems based on computer vision systems.

Full Text

Restricted Access

About the authors

Maria V. Tareeva

MIREA – Russian Technological University

Email: tareeva@mirea.ru
ORCID iD: 0000-0002-4985-1119
SPIN-code: 2508-1162

Cand. Sci. (Physics and Mathematics), Assistant professor of the Optical-Electronic Devices and Systems Department at the Institute of Advanced Technologies and Industrial Programming

Russian Federation, Moscow

Alina N. Kobysh

MIREA – Russian Technological University

Email: kobysh@mirea.ru
ORCID iD: 0009-0007-7658-4224
SPIN-code: 8836-0683

Cand. Sci. (Engineering), Acting Head of the Optical-Electronic Devices and Systems Department at the Institute of Advanced Technologies and Industrial Programming

Russian Federation, Moscow

Anastasia P. Shestakova

MIREA – Russian Technological University

Email: shestakova@mirea.ru
ORCID iD: 0000-0003-4995-246X
SPIN-code: 9363-5702

Cand. Sci. (Engineering), Assistant professor of the Optical-Electronic Devices and Systems Department at the Institute of Advanced Technologies and Industrial Programming

Russian Federation, Moscow

Vladimir V. Debelov

MIREA – Russian Technological University; Central Scientific Research Automobile and Automotive Engine Institute «NAMI»

Author for correspondence.
Email: vladimir.debelov@nami.ru
ORCID iD: 0000-0001-6050-0419
SPIN-code: 8701-7410

Cand. Sci. (Engineering), assistant professor, Head of the Software Technology Department of the Software Center

Russian Federation, Moscow; Moscow

References

  1. Gu B. Review: 40 years of laser-marking industrial applications. Proc. SPIE 6106, Photon Processing in Microelectronics and Photonics V. 2006;610601. doi: 10.1117/12.640838
  2. Marx C, Hustedt M, Hoja H, et al. (2013). Investigations on laser marking of plants and fruits. Biosystems Engineering. 2013;116(4):436–446. doi: 10.1016/j.biosystemseng.2013.10.005
  3. Sobotova L, Badida M. Laser marking as environment technology. Open Engineering. 2017;1(7):303–316. doi: 10.1515/eng-2017-0030
  4. Golnabi H, Asadpour A. Design and application of industrial machine vision systems. Robotics and Computer-Integrated Manufacturing. 2007;23(6):630–637. doi: 10.1016/j.rcim.2007.02.005
  5. Fedorov VB, Kharlamov SG, Fedorov AV. Image restoration using a discrete point spread function with consideration of finite pixel size. Russian Technological Journal. 2025;13(2):143–154. doi: 10.32362/2500-316X-2025-13-2-143–154 (In Russ.) EDN: GXAGAW
  6. Yurevich VI, Grimm VA, Afonyushkin AA, et al. Optical design and performance of F-Theta lenses for high-power and high-precision applications. Optical systems design 2015: optical design and engineering VI. SPIE; 2015;9626:437–452. doi: 10.1117/12.2190777
  7. Zhang Z. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000;22(11):1330–1334. doi: 10.1109/34.888718
  8. Garrido-Jurado S, Muñoz-Salinas R, Madrid-Cuevas FJ, et al. Automatic generation and detection of highly reliable fiducial markers under occlusion. Pattern Recognition. 2014;47(6):2280–2292. doi: 10.1016/j.patcog.2014.01.005
  9. Mur-Artal R, Montiel JMM, Tardós JD. ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE transactions on robotics. 2015;31(5):1147–1163. doi: 10.1109/TRO.2015.2463671
  10. Canny J. A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence. 1986;6:679–698. doi: 10.1109/TPAMI.1986.4767851
  11. Douglas DH, Peucker TK. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica. 1973;10(2):112–122. doi: 10.3138/FM57-6770-U75U-772
  12. Dawson-Howe KA. Practical Introduction to Computer Vision with OpenCV. Chichester: John Wiley & Sons; 2014.
  13. Klette R. Concise Computer Vision: An Introduction into Theory and Algorithms. London: Springer; 2014. doi: 10.1007/978-1-4471-6320-6

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Operating principle of a laser facility for chasing and marking, containing laser module (I), scanator module (II) and marker module (III): 1, laser radiation source; 2, laser facility fiber optic cable; 3, mirrors of the scanner unit; 4, F-Theta lenses; 5, lens view field with image grid; 6, probable focus areas: desired focus area (red) and possible focus area (pink).

Download (105KB)
Indexing metadata
3. Fig. 2. Window of the software for adjustment the marking field of the laser system for various types of distortions.

Download (373KB)
Indexing metadata
4. Fig. 3. Projection of a pinhole camera with a contact hole: , Origin of the camera reference frame; , origin of the image coordinates: , image of the object, , real image.

Download (118KB)
Indexing metadata
5. Fig. 4. Examples of lens distortion in a camera.

Download (81KB)
Indexing metadata
6. Fig. 5. Algorithm for selecting objects in an image for laser marking.

Download (288KB)
Indexing metadata
7. Fig. 6. Description of the image calibration algorithm.

Download (314KB)
Indexing metadata
8. Fig. 7. Block diagram of the image distortion calibration algorithm.

Download (274KB)
Indexing metadata
9. Fig. 8. Block diagram of the object position detection algorithm.

Download (337KB)
Indexing metadata
10. Fig. 9. Chip resistor on the laser view field during indication process (a) and marking process (b).

Download (231KB)
Indexing metadata
11. Fig. 10. Marked chip resistor before (a) and after (b) calibration algorithm optimization The size of the resistor is 3.2×6 mm.

Download (135KB)
Indexing metadata

Copyright (c) 2026 Eco-Vector

License URL: https://eco-vector.com/for_authors.php#07