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

You might also read

Related Articles

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

Sort by
Same author

Polarity-Programmable Bismuth Oxide Overlayers on Bi(111)/MoS<sub>2</sub> Heterostructures via Oxidation and Annealing.

The journal of physical chemistry letters·2026
Same author

External validation of a commercial AI system for pulmonary embolism detection on chest CTPA: a multicenter study.

Frontiers in molecular biosciences·2026
Same author

Automatic identification of different stage of Alzheimer's disease using multimodal MRI and artificial intelligence.

BMC medical imaging·2026
Same author

Prediction of Recurrence-Free Survival in Patients with Gastrointestinal Stromal Tumors via Mixed CT Radiomics-Postoperative Pathology Models.

Academic radiology·2026
Same author

MRI In Vivo Detection of Amyloid-β Protein Deposition in Different Brain Regions of Patients with AD and MCI.

Brain topography·2026
Same author

Alterations in the DTI-ALPS index and choroid plexus volume as brain-immune interfacing indicators in neuropsychiatric lupus erythematosus with inflammatory phenotype.

Lupus science & medicine·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

Related Experiment Video

Updated: Jul 24, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

Image Generation and Recognition for Railway Surface Defect Detection.

Yuwei Xia1, Sang Wook Han2, Hyock Ju Kwon1

  • 1Department of Mechanical and Mechatronics Engineering, University of Waterloo, 200 University Avenue West, Waterloo, ON N2L 3G1, Canada.

Sensors (Basel, Switzerland)
|July 11, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces RailGAN, an AI model that generates realistic railway defect images for training. This enhances non-destructive testing (NDT) accuracy, improving railway safety and reducing economic losses.

Keywords:
convolutional neural networkdataset expansionrailway defect detectionvisual inspection

More Related Videos

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.2K
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

581

Related Experiment Videos

Last Updated: Jul 24, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.2K
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

581

Area of Science:

  • Engineering
  • Artificial Intelligence
  • Materials Science

Background:

  • Railway surface defects pose significant economic and safety risks.
  • Accurate interpretation of non-destructive testing (NDT) data is crucial for defect detection.
  • Human error in NDT data interpretation is a frequent and unpredictable issue.

Purpose of the Study:

  • To address the scarcity of diverse railway defect images for training artificial intelligence (AI) models.
  • To propose and evaluate the RailGAN model for generating synthetic railway defect images.
  • To improve the accuracy and reliability of AI-driven railway defect detection.

Main Methods:

  • Developed RailGAN, an enhanced CycleGAN model incorporating a pre-sampling stage for railway tracks.
  • Tested two pre-sampling techniques: image-filtration and U-Net, on 20 real-time railway images.
  • Compared RailGAN with U-Net and the original CycleGAN for synthetic defect generation accuracy.

Main Results:

  • U-Net demonstrated more consistent image segmentation than image-filtration, less affected by pixel intensity.
  • RailGAN successfully generated synthetic defect patterns exclusively on the railway surface, unlike original CycleGAN.
  • Generated artificial crack images closely resemble real railway defects, suitable for training AI algorithms.

Conclusions:

  • The RailGAN model effectively generates high-quality synthetic railway defect images for AI training.
  • This approach can significantly enhance the accuracy of AI-based NDT for railway infrastructure.
  • The proposed method has the potential to increase railway safety and reduce economic losses.