Study of classification of coated paper brands using gloss images by contrastive learning

Takechiyo Kaai; Noriko Yata; Yoshitsugu Manabe; Shinichi Inoue

doi:10.1117/12.3020149

2 May 2024 Study of classification of coated paper brands using gloss images by contrastive learning

Takechiyo Kaai, Noriko Yata, Yoshitsugu Manabe, Shinichi Inoue

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 131643A (2024) https://doi.org/10.1117/12.3020149
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

This study aims to propose a paper classification method by gloss unevenness that can apply improvement of printing quality. At first, we take gloss images of coated papers that are same grade and different brands. After that, we classify them by contrastive learning. These accuracies are compared with supervised learning. Contrastive learning methods that we used in this study used Resnet-34 for CNN. As a result, they can classify approximately 53% rate. We will try implementing classification by voting for higher accuracy.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Takechiyo Kaai, Noriko Yata, Yoshitsugu Manabe, and Shinichi Inoue "Study of classification of coated paper brands using gloss images by contrastive learning", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 131643A (2 May 2024); https://doi.org/10.1117/12.3020149

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