Transformer-based brightness correction for finger vein images

Weijian Luo; Xiong Zhang

doi:10.1117/12.3006040

10 October 2023 Transformer-based brightness correction for finger vein images

Weijian Luo, Xiong Zhang

Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 127995F (2023) https://doi.org/10.1117/12.3006040
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia

Abstract

Finger vein authentication, as one of the identity authentication technologies, has the advantages of high stability, strong concealment, and the ability to perform liveness detection. However, the performance of finger vein authentication is susceptible to variations in lighting conditions across different scenes. Finger vein images with low or high brightness can lead to the loss of vein texture, resulting in authentication failures. To extend the application of finger vein authentication models with excellent performance in normal lighting conditions to diverse lighting scenarios, this paper proposes a Transformer-based finger vein image brightness correction network. Leveraging the global interaction capability of self-attention, the proposed network achieves comprehensive control over the brightness information of images and effectively adapts the input image's brightness to the target brightness distribution. Extensive experiments are conducted to validate the effectiveness of the brightness correction network. The experimental results confirm that the proposed approach can effectively correct the brightness of finger vein images, thereby improving the accuracy and stability of the authentication system across different lighting conditions.

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

Citation Download Citation

Weijian Luo and Xiong Zhang "Transformer-based brightness correction for finger vein images", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 127995F (10 October 2023); https://doi.org/10.1117/12.3006040

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
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Veins

Light sources and illumination

Transformers

Image processing

Feature extraction

Performance modeling

Education and training

Show All Keywords

Keywords/Phrases

Search In:

Publication Years