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 Experiment Video

Updated: Jul 4, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

A cancelable ear recognition system via optimized deep feature fusion.

Zeinab F Elsharkawy1, Eman M Omran2, Ayman A Eisa2

  • 1Engineering Department, Nuclear Research Center, Egyptian Atomic Energy Authority (EAEA), Cairo, Egypt. Zeinab_Elsharkawy@yahoo.com.

Scientific Reports
|June 13, 2026
PubMed
Summary

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

Efficient EOG-based movement classification in IoMT using machine learning algorithms for people with motor disabilities.

Disability and rehabilitation. Assistive technology·2026
Same author

Cervical lymph node TB: diagnostic yield and patient profile.

IJTLD open·2026
Same author

Automated diabetic retinopathy classification using vision transformers on optical confocal microscopy images.

Applied optics·2026
Same author

A two-stage deep learning framework for kidney disease detection using modified specular-free imaging and EfficientNetB2.

Scientific reports·2026
Same author

PCSA-Net: pyramid channel and spatial attention network for multiclass renal disease diagnosis using CT images.

Scientific reports·2026
Same author

A low-power VHF transceiver for airborne SAR with enhanced buried object detection using chirped signal processing.

Scientific reports·2026

This study introduces a novel deep learning framework for ear biometrics, enhancing security and accuracy. The system achieves high recognition rates, outperforming current methods for reliable identification.

Area of Science:

  • Biometrics and Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Deep Learning and Artificial Intelligence

Background:

  • Biometric authentication is crucial for secure identification, with ear biometrics offering unique advantages.
  • Challenges in ear recognition include variations in pose, scale, illumination, and contrast.
  • Existing methods require robust solutions to overcome these image variations.

Purpose of the Study:

  • To develop a secure and accurate deep learning-based ear recognition framework.
  • To address limitations in existing ear biometric systems by integrating advanced feature extraction and template protection.
  • To enhance the reliability of biometric authentication using unique human ear characteristics.

Main Methods:

  • A dual-stream Convolutional Neural Network (CNN) approach using MobileNetV3 and DenseNet-121 for feature extraction.

More Related Videos

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion
03:58

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion

Published on: January 17, 2025

Related Experiment Videos

Last Updated: Jul 4, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion
03:58

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion

Published on: January 17, 2025

  • Feature space optimization via the Multi-Learning Strategy Golden Eagle Optimization (MLSGEO) algorithm.
  • A Comb-filter-based mechanism for creating non-invertible, cancelable biometric templates to ensure privacy.

    • Main Results:

    • High recognition accuracies achieved on five benchmark datasets: AMI (99.90%), AWE (99.64%), IITD-I (99.78%), IITD-II (99.32%), and UERC (93.31%).
    • The proposed framework demonstrated superior performance compared to existing state-of-the-art ear recognition methods.
    • Effective data augmentation was used to mitigate dataset size limitations.

    Conclusions:

    • The developed deep learning framework offers a promising solution for secure and accurate biometric authentication.
    • The integration of advanced feature learning and robust template protection enhances system resilience and privacy.
    • Ear biometrics, when combined with innovative deep learning techniques, presents a strong potential for future identification applications.