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: Jan 19, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.3K

Deep neural network and data augmentation methodology for off-axis iris segmentation in wearable headsets.

Viktor Varkarakis1, Shabab Bazrafkan2, Peter Corcoran1

  • 1Department of Electronic Engineering, College of Engineering, National University of Ireland Galway, University Road, Galway, Ireland.

Neural Networks : the Official Journal of the International Neural Network Society
|September 22, 2019
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

Foldamers rescue synucleinopathy phenotypes in multiple in vitro and in vivo models.

Science translational medicine·2026
Same author

DiffusionTBAD: Rendering CTA images for type B aortic dissection diagnosis.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same author

ThermVision-DB: A synthetic LWIR thermal face dataset for privacy-preserving thermal vision research.

Data in brief·2026
Same author

The effect of prolonged conditionally automated driving on fatigue, physiological activity, and takeover performance: a driving simulator experiment.

Physiological measurement·2026
Same author

C3I-SynMicrosaccade: A pipeline and dataset for microsaccade recognition using neuromorphic event camera streams.

Data in brief·2026
Same author

Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

A novel data augmentation method creates extensive off-axis iris data. This trains a simple deep neural network for accurate iris segmentation, even in challenging conditions, suitable for augmented reality devices.

Area of Science:

  • Computer Vision
  • Biometrics
  • Machine Learning

Background:

  • Accurate iris segmentation is crucial for biometrics and augmented reality.
  • Existing methods often require high complexity and struggle with off-axis data.

Purpose of the Study:

  • To develop a data augmentation technique for generating off-axis iris data.
  • To train a low-complexity deep neural network for iris segmentation.
  • To evaluate the network's performance on both off-axis and frontal iris images.

Main Methods:

  • A data augmentation methodology was employed to create a large dataset of off-axis iris regions.
  • A low-complexity deep neural network was trained using this dataset.
  • The network's segmentation accuracy was evaluated on challenging off-axis and standard frontal iris images.
Keywords:
AR/VRData augmentationDeep neural networksIris segmentationOff-axis

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.1K

Related Experiment Videos

Last Updated: Jan 19, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.3K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.1K

Main Results:

  • The trained low-complexity network achieved high accuracy in segmenting off-axis iris regions.
  • The network also demonstrated high performance in segmenting frontal iris regions.
  • Performance favorably compared to state-of-the-art methods with significantly higher complexity.

Conclusions:

  • The proposed data augmentation and low-complexity network offer an effective solution for iris segmentation.
  • The network's efficiency makes it suitable for embedded systems, including augmented and mixed reality headsets.