Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Glycyrrhetinic Acid-Grafted Glycogen Nanoparticles Mediated Hepatic Delivery of Survivin Antisense Oligonucleotides for Liver Cancer-Targeted Gene Therapy.

ACS omega·2026
Same author

Engineering cytochromes for photocatalysis: Biohybrid assemblies for light-driven dye decoloration.

New biotechnology·2026
Same author

Multifunctional SiO<sub>2</sub>&PB particles composite coating on a titanium surface enhances the osseointegration of dental implants in diabetes.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Processing-dependent hepatic risk and benefit of Polygonum Multiflorum Radix: Integrated chemical profiling, in vivo validation and candidate quality control markers.

Journal of pharmaceutical and biomedical analysis·2026
Same author

Association Between Systemic Inflammation Indices and Recurrence Risk in Primary Budd-Chiari Syndrome.

Journal of inflammation research·2026
Same author

Small airway dysfunction: a shared, early, measurable, and potentially treatable trait across COPD, asthma, and fibrotic lung disease.

Frontiers in medicine·2026

Related Experiment Video

Updated: Jul 6, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

557

Multi scale-aware attention for pyramid convolution network on finger vein recognition.

Huijie Zhang1, Weizhen Sun1, Ling Lv2

  • 1School of Biological Science & Medical Engineering, Southeast University, Nanjing, 210096, China.

Scientific Reports
|January 4, 2024
PubMed
Summary

This study introduces a novel scale-aware attention module for finger vein recognition, enhancing accuracy with multi-scale feature extraction. The method effectively improves performance on low-quality images, advancing biometric identification technology.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Related Experiment Videos

Last Updated: Jul 6, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

557
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Area of Science:

  • Biometrics
  • Computer Vision
  • Pattern Recognition

Background:

  • Biometrics is a leading personal identification method.
  • Finger vein recognition offers stable, intrinsic traits with liveness detection.
  • Current Convolutional Neural Networks (CNNs) struggle with low-quality finger vein images due to limited input region coverage.

Purpose of the Study:

  • To address the challenge of effectively utilizing multi-scale features in finger vein recognition.
  • To enhance the discriminativeness of extracted features for improved recognition performance.
  • To develop a method that overcomes limitations of existing CNN-based approaches for finger vein recognition.

Main Methods:

  • Extraction of multi-scale features using pyramid convolution.
  • Proposal of a scale-aware attention (SA) module for dynamic weight adjustment in information aggregation.
  • Leveraging complementary details from different feature scales.

Main Results:

  • The proposed SA module enhances feature discriminativeness by effectively aggregating multi-scale information.
  • Experimental validation on public and internal datasets demonstrates significant improvements in finger vein recognition performance.
  • The method proves effective even with low-quality finger vein images.

Conclusions:

  • The developed scale-aware attention module significantly boosts finger vein recognition accuracy.
  • Pyramid convolution and scale attention offer a robust approach for handling multi-scale features.
  • This research contributes to more reliable and effective biometric identification systems.