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

Veins as Blood Reservoirs01:10

Veins as Blood Reservoirs

7.1K
Veins, while chiefly responsible for circulating blood back to the heart, also function as storage vessels for blood. They house approximately 64 percent of the body's total blood volume, a feat made possible by their high capacitance—the inherent ability to expand and accommodate large volumes of blood, even under low pressure. The large diameter and thin walls of veins augment their distensibility, significantly more so than arteries, due to their classification as capacitance...
7.1K
Veins of Upper Limbs01:17

Veins of Upper Limbs

2.9K
The human circulatory system, a marvel of biological engineering, is a complex network of vessels that transport blood throughout the body. Among these, the veins responsible for carrying blood from the upper limbs are divided into two categories: deep and superficial.
The deep venous system is primarily composed of the ulnar and radial veins. The ulnar vein, which drains the fingers through the superficial palmar venous arches, and the radial vein, which serves the palms via the deep palmar...
2.9K
Veins01:17

Veins

8.0K
Veins are an integral part of our circulatory system, serving as the blood vessels that transport blood from all body regions to the heart. They are a network of hollow tubes that carry blood low in oxygen from the body's cells back to the heart for reoxygenation. Veins are crucial for maintaining the body's overall fluid balance and the continuous circulation of blood.
Structure of Veins:
The structure of veins is specifically designed to assist in the low-pressure transportation of...
8.0K
Veins of Lower Limbs01:15

Veins of Lower Limbs

1.8K
The human body consists of an intricate network of veins responsible for the crucial task of blood drainage from the lower limbs. These veins can be categorized into two main types: deep veins and superficial veins.
Formed by the union of the medial and lateral plantar veins, the posterior tibial vein, rising through the calf muscle, assimilates the fibular vein. The anterior tibial vein, a superior extension of the foot's dorsalis pedis vein, merges with the posterior tibial vein at the...
1.8K

You might also read

Related Articles

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

Sort by
Same author

Adversarial CAM Guidance for Chest X-Ray Classification: Reducing Framing Sensitivity with Mask Supervision.

Biomimetics (Basel, Switzerland)·2026
Same author

Weighted knowledge distillation for semi-supervised segmentation of maxillary sinus in panoramic X-ray images.

Scientific reports·2026
Same author

KDOSS-net: Knowledge distillation-based outpainting and semantic segmentation network for crop and weed images.

Plant phenomics (Washington, D.C.)·2025
Same author

Biodegradable Plastics as Sustainable Alternatives: Advances, Basics, Challenges, and Directions for the Future.

Materials (Basel, Switzerland)·2025
Same author

Data-Driven Printability Modeling of Hydrogels for Precise Direct Ink Writing Based on Rheological Properties.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Beyond Binary: Improving Signed Message Passing in Graph Neural Networks for Multi-Class Graphs.

IEEE transactions on pattern analysis and machine intelligence·2025

Related Experiment Video

Updated: Nov 21, 2025

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents
04:19

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents

Published on: April 19, 2019

21.8K

Finger-Vein Recognition Using Heterogeneous Databases by Domain Adaption Based on a Cycle-Consistent Adversarial

Kyoung Jun Noh1, Jiho Choi1, Jin Seong Hong1

  • 1Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro, 1-gil, Jung-gu, Seoul 04620, Korea.

Sensors (Basel, Switzerland)
|January 16, 2021
PubMed
Summary
This summary is machine-generated.

Domain adaptation using CycleGAN significantly improves finger-vein recognition accuracy across different databases. This method enhances performance on unobserved data, overcoming limitations of conventional systems.

Keywords:
HKPolyU-DBSDUMLA-HMT-DBcamera positioncycle-consistent adversarial networksdomain adaptationfinger positionfinger-vein recognitionheterogeneous databaselightingunobserved database

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.1K

Related Experiment Videos

Last Updated: Nov 21, 2025

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents
04:19

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents

Published on: April 19, 2019

21.8K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.1K

Area of Science:

  • Biometrics
  • Computer Vision
  • Machine Learning

Background:

  • Conventional finger-vein recognition systems suffer performance degradation when tested on databases different from their training set.
  • Variations in camera position, finger placement, and lighting cause differing image characteristics across databases, even for the same biometric modality.
  • Existing research lacks effective methods for improving recognition accuracy on unobserved or heterogeneous finger-vein databases.

Purpose of the Study:

  • To propose and evaluate a novel method for enhancing finger-vein recognition accuracy using domain adaptation.
  • To address the challenge of performance degradation when finger-vein systems encounter data from different sources.
  • To improve the recognition accuracy of unobserved data by bridging the gap between heterogeneous databases.

Main Methods:

  • Utilized cycle-consistent adversarial networks (CycleGAN) for domain adaptation between heterogeneous finger-vein databases.
  • Conducted experiments using two distinct open-source databases: Shandong University homologous multi-modal traits finger-vein database (SDUMLA-HMT-DB) and Hong Kong Polytech University finger-image database (HKPolyU-DB).
  • Evaluated the proposed method's effectiveness in improving recognition accuracy on cross-database testing scenarios.

Main Results:

  • Achieved an equal error rate (EER) of 0.85% when training with SDUMLA-HMT-DB and testing with HKPolyU-DB, representing a 33.1% improvement over the second-best method.
  • Obtained an EER of 3.4% when training with HKPolyU-DB and testing with SDUMLA-HMT-DB, showing a 4.8% improvement compared to the second-best method.
  • Demonstrated significant enhancement in cross-database recognition accuracy for finger-vein systems.

Conclusions:

  • The proposed domain adaptation method using CycleGAN effectively improves finger-vein recognition accuracy across heterogeneous databases.
  • This approach successfully enhances the recognition of unobserved data, mitigating performance degradation issues.
  • The findings suggest a promising direction for developing more robust and generalizable biometric systems.