A metal surface defect detection method based on attention mechanism and softpool

Linlin Wang; Xiaoyu Fang; Tong Zhang; Wenjie Liang; Chang Liu

doi:10.1117/12.2667074

27 January 2023 A metal surface defect detection method based on attention mechanism and softpool

Linlin Wang, Xiaoyu Fang, Tong Zhang, Wenjie Liang, Chang Liu

Proceedings Volume 12550, International Conference on Optical and Photonic Engineering (icOPEN 2022); 125501F (2023) https://doi.org/10.1117/12.2667074
Event: International Conference on Optical and Photonic Engineering (icOPEN 2022), 2022, ONLINE, China

Abstract

Due to the influence of various factors in the production process of metal industrial products, there will be many kinds of defects on the surface. Quality inspection on the surface of metal products is particularly important to ensure the quality of industrial production. This paper based on the Inception-Resnet-V2 network to study the defect detection of steel plates. The network model is improved by adding a CBAM attention module to the original network, which increases the weight of defect-related information, reduces the interference of useless features, and then improves detection accuracy. At the same time, we use Softpool replace the traditional Maxpool pooling method to retain fine- grained feature information and fully capture more image features. Then the detection accuracy can be further improved. In this paper, the steel plate defect images are used as the dataset to train the improved network model. The improved network model can effectively identify cracks, impurities, pitting surface, oxide scale, scratches and other defects on the surface of steel plate. We compare the detection accuracy of the proposed network model with the VGG16, Resnet50 and YOLOv5 network models. The results show that the proposed network architecture significantly improves the defect detection accuracy

Citation Download Citation

Linlin Wang, Xiaoyu Fang, Tong Zhang, Wenjie Liang, and Chang Liu "A metal surface defect detection method based on attention mechanism and softpool", Proc. SPIE 12550, International Conference on Optical and Photonic Engineering (icOPEN 2022), 125501F (27 January 2023); https://doi.org/10.1117/12.2667074

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Metals

Defect detection

Education and training

Data modeling

Content addressable memory

Convolution

Deep learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years