Belt defect detection based on f-AnoGAN

Lei Yun; Jinming Wang; Liqing Yang; Bin Hao; Fei Zhang; Lu Gao

doi:10.1117/12.3004875

16 August 2023 Belt defect detection based on f-AnoGAN

Lei Yun, Jinming Wang, Liqing Yang, Bin Hao, Fei Zhang, Lu Gao

Proceedings Volume 12787, Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023); 1278709 (2023) https://doi.org/10.1117/12.3004875
Event: 6th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE 2023), 2023, Shenyang, China

Abstract

A belt defect detection model based on unsupervised generative adversarial network is proposed for the problem of low number of defective samples in belt defect detection. The model is trained on defect-free normal samples and the detection results are obtained by calculating the outliers between the input samples and the reconstructed samples at the time of detection. Considering the information loss problem of the encoder compressing the input samples, this paper adds a selfattention mechanism to the model to enhance the extraction of useful features. In addition, the LeakyPeLU activation function in the model is replaced with PReLU to improve the fitting ability of the model, and the method is experimentally proven to achieve better image reconstruction results. The experimental results show that the accuracy of the assay using this method is 98.13%, AUC value is 99.89% and AP value is 99.75%, which was better than the other two comparative models. The method has good reconfiguration and defect detection capabilities.

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

Citation Download Citation

Lei Yun, Jinming Wang, Liqing Yang, Bin Hao, Fei Zhang, and Lu Gao "Belt defect detection based on f-AnoGAN", Proc. SPIE 12787, Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023), 1278709 (16 August 2023); https://doi.org/10.1117/12.3004875

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