CGS-YOLOv5: a defect detection algorithm for PCB board based on YOLOv5 algorithm

Huizhong Zhu; Jianjun Jiang; Yinghe Wang

doi:10.1117/12.3026220

15 March 2024 CGS-YOLOv5: a defect detection algorithm for PCB board based on YOLOv5 algorithm

Huizhong Zhu, Jianjun Jiang, Yinghe Wang

Proceedings Volume 13075, Second International Conference on Physics, Photonics, and Optical Engineering (ICPPOE 2023); 1307515 (2024) https://doi.org/10.1117/12.3026220
Event: Second International Conference on Physics, Photonics, and Optical Engineering (ICPPOE 2023), 2023, Kunming, China

Abstract

Printed Circuit Board (PCB) is one of the core components of electronic equipment, ensuring the quality and reliability of PCB board is essential for product performance, life and safety. In view of the low detection accuracy and large number of model parameters in the traditional algorithm of PCB, this paper improves YOLOv5 model, using the ghost module instead of the standard convolution layer, to ameliorate the performance, make the model more lightweight. Employ coordinate attention mechanism module, improve the detection of PCB Small goals. Adopt the SIOU loss function, enhance the precision of the model. The empirical findings confirm that the improved YOLOv5 improves the average accuracy by 1.4% over a 47% reduction in parameter size.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Huizhong Zhu, Jianjun Jiang, and Yinghe Wang "CGS-YOLOv5: a defect detection algorithm for PCB board based on YOLOv5 algorithm", Proc. SPIE 13075, Second International Conference on Physics, Photonics, and Optical Engineering (ICPPOE 2023), 1307515 (15 March 2024); https://doi.org/10.1117/12.3026220

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