Steel surface defect detection based on improved YOLOv8

Meihong Huang; Zhimeng Cai

doi:10.1117/12.3011950

7 December 2023 Steel surface defect detection based on improved YOLOv8

Meihong Huang, Zhimeng Cai

Proceedings Volume 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023); 129415C (2023) https://doi.org/10.1117/12.3011950
Event: Third International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 203), 2023, Yinchuan, China

Abstract

In this paper, an improved YOLOv8 algorithm is proposed for the detection of steel surface defects. The proposed method replaces the C2F module of the backbone network with the GhostNetv2 module, aggregating both local and long-range information to enhance the model's expressive power. Additionally, a progressive feature pyramid structure is constructed to accelerate model training speed and strengthen feature extraction capability. Moreover, an efficient multi-scale attention mechanism is introduced to optimize the network structure, combining global and local information to extract more comprehensive target features. Experimental results demonstrate that the improved YOLOv8 network model exhibits excellent detection performance, achieving the mAP of 77.5% on the NEU-DET dataset, which is a 3.5% improvement compared to the original YOLOv8 network model.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Meihong Huang and Zhimeng Cai "Steel surface defect detection based on improved YOLOv8", Proc. SPIE 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), 129415C (7 December 2023); https://doi.org/10.1117/12.3011950

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