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

GPRASP1 Safeguards Endothelial Aspartate Metabolism to Prevent Pulmonary Hypertension Associated With Heart Failure With Preserved Ejection Fraction.

Circulation·2026
Same author

Separation and Characterization of Self-Assembled Nanoparticles from <i>Rheum palmatum</i> L.-<i>Salvia miltiorrhiza</i> Bunge Extract and Their Renoprotective Effects in Acute Kidney Injury.

Antioxidants (Basel, Switzerland)·2026
Same author

BRD4 directs myofiber identity and metabolic adaptation through CHD4 cooperation.

Nature communications·2026
Same author

How social support impacts depression in Chinese emerging adults: mediators of cognitive reappraisal and loneliness.

Frontiers in psychology·2026
Same author

Soil microbial community assembly drives ecosystem multifunctionality under grazing disturbance by regulating diversity and network structure.

Scientific reports·2026
Same author

LETM1 deacetylation attenuates calcium overload-mediated mitochondrial injury and protects the intestine from ischemia/reperfusion damage.

Life sciences·2026
See all related articles

Related Experiment Video

Updated: Jun 12, 2025

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

485

A lightweight parallel attention residual network for tile defect recognition.

Cheng Lv1, Enxu Zhang1, Guowei Qi1

  • 1School of Mechanical Engineering, Xijing University, Xi'an, 710123, China.

Scientific Reports
|September 19, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a new method for detecting defects on magnetic tiles, crucial for permanent magnet motor performance. The Lightweight Parallel Attention Residual Network (LPAR-Net) achieves 93.63% accuracy, outperforming existing models for industrial defect recognition.

Keywords:
Attention mechanismDeep learningMachine visionMetal surface defects

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
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

2.7K

Related Experiment Videos

Last Updated: Jun 12, 2025

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

485
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
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

2.7K

Area of Science:

  • Materials Science
  • Computer Vision
  • Industrial Automation

Background:

  • Permanent magnet motors are vital in industrial production, and magnetic tile quality directly impacts their performance.
  • Detecting small and reflective surface defects on magnetic tiles is challenging due to unclear image features.

Purpose of the Study:

  • To develop an effective method for detecting defects on magnetic tile surfaces, addressing challenges of unclear features and small defect sizes.
  • To improve the recognition accuracy of magnetic tile defects in industrial settings.

Main Methods:

  • Image processing using linear variation to enhance detail features.
  • Development of the Attention Parallel Residual Convolution Block (APR) and Lightweight Parallel Attention Residual Network (LPAR-Net) incorporating MobileNetV2's inverted bottleneck structure.
  • Integration of an improved Channel Attention Module (CBAM) within the APR Block for enhanced feature extraction, including a 7x7 convolution for broader spatial feature capture.

Main Results:

  • The proposed LPAR-Net achieved an accuracy of 93.63% on the magnetic tile defect dataset.
  • LPAR-Net demonstrated superior performance compared to mainstream image classification models like DenseNet, MobileNet, and ConvNext.
  • Validation on a strip steel surface defect dataset confirmed the method's robust recognition capability.

Conclusions:

  • The LPAR-Net method significantly improves the accuracy and capability of magnetic tile defect detection.
  • This approach offers a promising solution for quality control in industrial manufacturing processes involving permanent magnet motors.
  • The study contributes a new dataset and a validated deep learning model for surface defect analysis.