Research on aluminum profile surface defect detection based on an improved YOLOv5 algorithm

Liang Yang; Bo Liu; Lizhong Zhu

doi:10.1117/12.3032930

5 July 2024 Research on aluminum profile surface defect detection based on an improved YOLOv5 algorithm

Liang Yang, Bo Liu, Lizhong Zhu

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 131840S (2024) https://doi.org/10.1117/12.3032930
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

As aluminum profiles become increasingly popular in aerospace and aircraft manufacturing, the detection and quality management of surface defects in aluminum profiles are crucial. This study enhances the YOLOv5 algorithm for detecting surface defects in aluminum profiles, using images from a company's production line. It introduces K-Means++ to the adaptive anchor box algorithm for optimal initial center selection in clustering. Additionally, C3 was replaced with C2f, and the SE attention mechanism was introduced. Experiments demonstrate that the optimized YOLOv5 algorithm performs excellently. It not only achieves faster detection speeds but also improves detection accuracy, effectively addressing the challenge of low recall rates for small and slender targets.

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

Citation Download Citation

Liang Yang, Bo Liu, and Lizhong Zhu "Research on aluminum profile surface defect detection based on an improved YOLOv5 algorithm", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 131840S (5 July 2024); https://doi.org/10.1117/12.3032930

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