PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification

Xu, Jiafeng; Jia, Dawei; Lin, Zhizhe; Zhou, Teng; Wu, Jie; Tang, Lin

doi:10.3390/electronics13214160

Open AccessArticle

PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification

by

Jiafeng Xu

^1,*

,

Dawei Jia

¹,

Zhizhe Lin

^2,*

,

Teng Zhou

^2,3

,

Jie Wu

⁴ and

Lin Tang

⁵

¹

School of Immigration Management, China People’s Police University, Guangzhou 510663, China

²

School of Cyberspace Security, Hainan University, Haikou 570228, China

³

Yangtze Delta Region Institute, University of Electronic Science and Technology of China, Quzhou 324003, China

⁴

School of Wu Shu, Henan University, Kaifeng 610054, China

⁵

School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu 610106, China

^*

Authors to whom correspondence should be addressed.

Electronics 2024, 13(21), 4160; https://doi.org/10.3390/electronics13214160

Submission received: 24 September 2024 / Revised: 15 October 2024 / Accepted: 21 October 2024 / Published: 23 October 2024

Download

Browse Figures

Review Reports Versions Notes

Abstract

Passport background texture classification has always been an important task in border checks. Current manual methods struggle to achieve satisfactory results in terms of consistency and stability for weakly textured background images. For this reason, this study designs and develops a CNN and Transformer complementary network (PBNet) for passport background texture image classification. We first design two encoders by Transformer and CNN to produce complementary features in the Transformer and CNN domains, respectively. Then, we cross-wisely concatenate these complementary features to propose a feature enhancement module (FEM) for effectively blending them. In addition, we introduce focal loss to relieve the overfitting problem caused by data imbalance. Experimental results show that our PBNet significantly surpasses the state-of-the-art image segmentation models based on CNNs, Transformers, and even Transformer and CNN combined models designed for passport background texture image classification.

Keywords: passport; background texture; Convolutional Neural Network; Transformer

Share and Cite

MDPI and ACS Style

Xu, J.; Jia, D.; Lin, Z.; Zhou, T.; Wu, J.; Tang, L. PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification. Electronics 2024, 13, 4160. https://doi.org/10.3390/electronics13214160

AMA Style

Xu J, Jia D, Lin Z, Zhou T, Wu J, Tang L. PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification. Electronics. 2024; 13(21):4160. https://doi.org/10.3390/electronics13214160

Chicago/Turabian Style

Xu, Jiafeng, Dawei Jia, Zhizhe Lin, Teng Zhou, Jie Wu, and Lin Tang. 2024. "PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification" Electronics 13, no. 21: 4160. https://doi.org/10.3390/electronics13214160

APA Style

Xu, J., Jia, D., Lin, Z., Zhou, T., Wu, J., & Tang, L. (2024). PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification. Electronics, 13(21), 4160. https://doi.org/10.3390/electronics13214160

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI