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

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

937
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
937
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.4K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.4K

You might also read

Related Articles

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

Sort by
Same author

When AI and Experts Agree on Error: Intrinsic Ambiguity in Dermatoscopic Images.

Journal of imaging·2026
Same author

Skin Lesion Classification Through Test Time Augmentation and Explainable Artificial Intelligence.

Journal of imaging·2025
Same author

Attention-based deep learning framework to recognize diabetes disease from cellular retinal images.

Biochemistry and cell biology = Biochimie et biologie cellulaire·2023
Same author

The Development of an Intelligent Agent to Detect and Non-Invasively Characterize Lung Lesions on CT Scans: Ready for the "Real World"?

Cancers·2023
Same author

Deep Learning-Based Automatic Detection of Ships: An Experimental Study Using Satellite Images.

Journal of imaging·2022
Same author

Sign and Human Action Detection Using Deep Learning.

Journal of imaging·2022

Related Experiment Video

Updated: Jul 18, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

Enhancing Fingerprint Liveness Detection Accuracy Using Deep Learning: A Comprehensive Study and Novel Approach.

Deep Kothadiya1, Chintan Bhatt2, Dhruvil Soni2

  • 1U & P U Patel Department of Computer Engineering, CHA-RUSAT Campus, Charotar University of Science and Technology, Petlad 388421, India.

Journal of Imaging
|August 25, 2023
PubMed
Summary

This study enhances fingerprint liveness detection using deep learning with sequential attention models and ResNet convolutions. The improved method boosts accuracy in preventing unauthorized access and phishing attempts.

Keywords:
ResNet50attention modelcomputer visiondeep learningliveness detection

More Related Videos

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

570
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

638

Related Experiment Videos

Last Updated: Jul 18, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
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

570
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

638

Area of Science:

  • Biometrics and Security
  • Computer Vision
  • Deep Learning

Background:

  • Biometric systems, particularly fingerprint recognition, are increasingly popular for individual identification.
  • Liveness detection is crucial for preventing unauthorized access and sophisticated phishing attacks.
  • Deep learning, especially computer vision techniques, shows significant promise in image analysis tasks.

Purpose of the Study:

  • To propose and evaluate an advanced deep learning methodology for fingerprint liveness detection.
  • To enhance feature learning in fingerprint images using sequential attention mechanisms.
  • To compare the performance of the proposed method against state-of-the-art deep learning models.

Main Methods:

  • A novel methodology combining ResNet convolutions with sequential spatial attention (SA) and channel attention (CA) models.
  • Implementation of a three-fold sequential attention model integrated with five convolutional layers.
  • Evaluation using different pooling strategies (Max, Average, Stochastic) on the LivDet-2021 dataset.
  • Comparative analysis with established Convolutional Neural Networks (CNNs) like DenseNet121, VGG19, InceptionV3, and ResNet50.
  • Assessment of ResNet34 and ResNet50 models for feature extraction, enhanced by the sequential attention model.
  • Utilization of a Multilayer Perceptron (MLP) classifier with a fully connected layer for final predictions.

Main Results:

  • The proposed sequential attention model significantly enhances feature learning for fingerprint liveness detection.
  • Performance was evaluated across various pooling strategies, demonstrating robustness.
  • Comparisons showed competitive or superior results against several state-of-the-art CNN architectures.
  • The integration of attention mechanisms with ResNet models yielded notable improvements in feature extraction.

Conclusions:

  • The developed deep learning approach, incorporating sequential attention and ResNet, offers a powerful solution for robust fingerprint liveness detection.
  • The method effectively improves the accuracy and reliability of biometric security systems.
  • Further research can explore variations in attention mechanisms and network architectures for even greater performance gains.