Steel surface defect detection based on improved CenterNet algorithm

Shuaixi Yu

doi:10.1117/12.2670493

1 June 2023 Steel surface defect detection based on improved CenterNet algorithm

Shuaixi Yu

Proceedings Volume 12625, International Conference on Mathematics, Modeling, and Computer Science (MMCS2022); 126252H (2023) https://doi.org/10.1117/12.2670493
Event: International Conference on Mathematics, Modeling and Computer Science (MMCS2022),, 2022, Wuhan, China

Abstract

In the steady development of social economy and science and technology, the steel surface defect detection technology in the industrial field is the main issue discussed in the academic circle at present. It can quickly find the defects in the steel surface from the basis, help the industrial field to improve product quality, reduce the safety risk of product application. On the basis of understanding the research status of improved CenterNet algorithm and starting with the current application of industrial steel, this paper deeply discusses the steel surface defect detection technology based on improved CenterNet algorithm. The final experimental results show that this method can improve the accuracy of practical detection, and the specific detection time is the same as the original network, but it has strong practicability and meets the needs of technological development in the industrial field in the new era.

Citation Download Citation

Shuaixi Yu "Steel surface defect detection based on improved CenterNet algorithm", Proc. SPIE 12625, International Conference on Mathematics, Modeling, and Computer Science (MMCS2022), 126252H (1 June 2023); https://doi.org/10.1117/12.2670493

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available