Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

PG-MCTFormer: A Prior-Guided Multi-Scale Convolutional Transformer for Interpretable Motor Imagery EEG Classification.

Biomimetics (Basel, Switzerland)·2026

Same author

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026

Same author

Amorphous Ru-bda MCOF: A Frontier in Heterogeneous Molecular Catalysis for Water Oxidation.

Inorganic chemistry·2026

Same author

Fluorescence spectroscopy, 3D-QSAR, and molecular dynamics analyses reveal the interaction mechanisms of flavonoids with lysozyme.

Food chemistry·2026

Same author

Fabrication and Characterization of High Internal Phase Pickering Emulsion Gels Stabilized by Hesperidin and Lysozyme.

Foods (Basel, Switzerland)·2026

Same author

Structural and mechanistic insights into the inhibition of Plasmodium falciparum MDR1.

Nature communications·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 3, 2025

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

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

Published on: December 15, 2023

An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural

Guoyang Liu¹, Weidong Zhou¹, Lan Tian¹

¹School of Microelectronics, Shandong University, Jinan 250100, China.

Sensors (Basel, Switzerland)

|June 2, 2021

Summary

This summary is machine-generated.

This study introduces a condensed 2-channel convolutional neural network (CNN) for efficient and accurate iris recognition, even with limited training data. The novel approach enhances performance and reduces computational load for real-time identification and verification.

Keywords:

convolutional neural network deep learning iris recognition network pruning online augmentation

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Nov 3, 2025

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

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

Published on: December 15, 2023

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Computer Science
Biometrics
Artificial Intelligence

Background:

Deep learning, particularly Convolutional Neural Networks (CNNs), shows promise in iris recognition but demands extensive training data and high computational resources.
Classic iris recognition methods offer lower complexity but lack the automatic feature extraction capabilities of deep learning.

Purpose of the Study:

To develop an efficient and accurate iris recognition system using a novel condensed 2-channel CNN (2-ch CNN) that requires fewer training samples.
To address the high computational complexity associated with traditional CNN-based iris recognition methods.

Main Methods:

A multi-branch CNN with online augmentation and radial attention layers was designed as a base classifier.
Model pruning techniques (branch and channel pruning) were applied based on weight distribution analysis.
Fast fine-tuning was optionally used to improve pruned model performance and reduce computational burden.
The encoding capability of the 2-ch CNN was investigated for large-scale database applications.

Main Results:

The proposed condensed 2-ch CNN achieved efficient and accurate iris identification and verification with limited training data.
Pruning and fine-tuning strategies significantly improved performance while reducing computational complexity.
The developed iris recognition scheme demonstrated suitability for large databases.
Gradient-based analysis confirmed the algorithm's robustness against image contaminations.

Conclusions:

The novel condensed 2-ch CNN offers a computationally efficient and accurate solution for iris recognition, suitable for real-time applications and large-scale databases.
The method effectively mitigates the need for extensive training data and high computational resources common in deep learning approaches.
The algorithm demonstrates robustness, making it reliable in practical, real-world scenarios.