Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology

Machine-vision-based Defect Detection Using Circular Hough Transform in Laser Welding

Authors
Qiao Ding, Jianhua Ji, Feng Gao, Yatao Yang
Corresponding Author
Qiao Ding
Available Online March 2016.
DOI
https://doi.org/10.2991/icmmct-16.2016.141How to use a DOI?
Keywords
laser welding, machine vision, Circular Hough Transform, defect detection
Abstract
In the field of laser welding, image processing technology is the general method to detect defects on the surface of the seam. Here the Hough Transform is introduced into the defect detection and the accuracy is greatly improved. The process is to use the industrial CCD(Charge-coupled Device) camera for image acquisition, then use Canny operator for edge detection, use Circular Hough Transform to locate the weld seam position, and finally compare the number of continuous pixels with the defect criteria to report detection results. Experimental data show that the false positive rate and false negative rate are greatly reduced after the Hough Transform is introduced into the defect detection, which has met the industrial requirements.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
Series
Advances in Engineering Research
Publication Date
March 2016
ISBN
978-94-6252-165-0
ISSN
2352-5401
DOI
https://doi.org/10.2991/icmmct-16.2016.141How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Qiao Ding
AU  - Jianhua Ji
AU  - Feng Gao
AU  - Yatao Yang
PY  - 2016/03
DA  - 2016/03
TI  - Machine-vision-based Defect Detection Using Circular Hough Transform in Laser Welding
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
PB  - Atlantis Press
SP  - 729
EP  - 732
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-16.2016.141
DO  - https://doi.org/10.2991/icmmct-16.2016.141
ID  - Ding2016/03
ER  -