Deep learning-based object detection algorithm for mask surface defects

Yuanzhang Zhao; Shengling Geng II

doi:10.1117/12.2635390

6 May 2022 Deep learning-based object detection algorithm for mask surface defects

Yuanzhang Zhao, Shengling Geng II

Proceedings Volume 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022); 122561R (2022) https://doi.org/10.1117/12.2635390
Event: 2022 International Conference on Electronic Information Engineering, Big Data and Computer Technology, 2022, Sanya, China

Abstract

In order to solve the problem of product defects in the mask production process. In this paper, an algorithm for target detection of mask surface defects based on YOLOv5 is proposed. The industrial-like camera and industrial-like light source are used to collect the data set, and the data set is filtered and manually labeled. The extracted features of mask defects, broken ear straps, and solder joints are trained and tested using the YOLOv5 algorithm. The experiments show that the YOLOv5 algorithm can effectively identify various defects on the mask surface, improve mask production quality and reduce mask production cost.

Citation Download Citation

Yuanzhang Zhao and Shengling Geng II "Deep learning-based object detection algorithm for mask surface defects", Proc. SPIE 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022), 122561R (6 May 2022); https://doi.org/10.1117/12.2635390

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