Defective samples simulation through neural style transfer for automatic surface defect segment

Taoran Wei; Danhua Cao; Xingru Jiang; Caiyun Zheng; Lizhe Liu

doi:10.1117/12.2540464

12 March 2020 Defective samples simulation through neural style transfer for automatic surface defect segment

Taoran Wei, Danhua Cao, Xingru Jiang, Caiyun Zheng, Lizhe Liu

Proceedings Volume 11439, 2019 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems; 1143904 (2020) https://doi.org/10.1117/12.2540464
Event: 2019 International Conference on Optical Instruments and Technology, 2019, Beijing, China

Abstract

Owing to the lack of defect samples in industrial product quality inspection, trained segmentation model tends to overfit when applied online. To address this problem, we propose a defect sample simulation algorithm based on neural style transfer. The simulation algorithm requires only a small number of defect samples for training, and can efficiently generate simulation samples for next-step segmentation task. In our work, we introduce a masked histogram matching module to maintain color consistency of the generated area and the true defect. To preserve the texture consistency with the surrounding pixels, we take the fast style transfer algorithm to blend the generated area into the background. At the same time, we also use the histogram loss to further improve the quality of the generated image. Besides, we propose a novel structure of segment net to make it more suitable for defect segmentation task. We train the segment net with the real defect samples and the generated simulation samples separately on the button datasets. The results show that the F1 score of the model trained with only the generated simulation samples reaches 0.80, which is better than the real sample result.

Citation Download Citation

Taoran Wei, Danhua Cao, Xingru Jiang, Caiyun Zheng, and Lizhe Liu "Defective samples simulation through neural style transfer for automatic surface defect segment", Proc. SPIE 11439, 2019 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems, 1143904 (12 March 2020); https://doi.org/10.1117/12.2540464

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
12 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Computer simulations

Statistical modeling

Image quality

Data modeling

Image processing algorithms and systems

Image segmentation

Inspection

Show All Keywords

Keywords/Phrases

Search In:

Publication Years