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

Neurochondrin promotes U5 snRNP maturation by regulating AAR2 release from PRPF8.

Nucleic acids research·2026
Same author

Prevalence and Epidemiological Characteristics of <i>Mycoplasma synoviae</i> Infection in Chickens in Mainland China.

Animals : an open access journal from MDPI·2026
Same author

β-TrCP targets nucleolin and modulates phase separation to restrict ribosome biogenesis in myocardial infarction hearts.

Cellular signalling·2026
Same author

Bilateral Myeloid Sarcoma of Breast: A Case Report and Discussion.

European journal of breast health·2026
Same author

Melatonin in Livestock Production: Bridging Chronobiology, Health, and Sustainable Outcomes.

The Journal of nutrition·2026
Same author

Synergy of Spin States, Active Centers, and H Adsorption Sites on <i>d</i>-<i>p</i> Hybridized Fe-Sn-N<sub>6</sub>-C Dual-Atom Catalysts for Enhanced Oxygen Reduction Reaction.

Journal of the American Chemical Society·2026

Related Experiment Video

Updated: Jul 21, 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

572

Bearing surface defect detection based on improved convolutional neural network.

Xian Fu1, Xiao Yang1, Ningning Zhang1

  • 1Department of Computer and Information Engineering, Hubei Normal University, Huangshi 435000, China.

Mathematical Biosciences and Engineering : MBE
|July 28, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an improved YOLOv5 algorithm for automatic visual inspection, enhancing defect detection accuracy and speed. The new method significantly boosts performance in identifying bearing appearance defects, reducing costs and improving efficiency.

Keywords:
attention mechanismdefect detectionlightweight networktarget detection

More Related Videos

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.4K
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

Related Experiment Videos

Last Updated: Jul 21, 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

572
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.4K
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

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional visual inspection relies on subjective experience, struggling with subtle defects.
  • Accurate identification of dense and non-significant defects is challenging for human inspectors.

Purpose of the Study:

  • To develop an automatic object detection algorithm for enhanced visual inspection.
  • To improve the accuracy and efficiency of detecting bearing appearance defects.

Main Methods:

  • Implemented an improved YOLOv5 object detection algorithm.
  • Utilized K-means++ for anchor calculation and incorporated Coordinate Attention (CA) mechanism.
  • Added a new detection layer and replaced the backbone with MobileNetV3 for efficiency.

Main Results:

  • Achieved 85.87% mean Average Precision (mAP), a 6.44% improvement over standard YOLOv5.
  • Reduced single image detection time to 54ms, a 50% speed increase compared to YOLOv5.
  • Demonstrated rapid and accurate detection of bearing appearance defects.

Conclusions:

  • The proposed algorithm significantly enhances the accuracy and speed of visual inspection for bearing defects.
  • The improvements lead to increased detection efficiency and reduced operational costs.
  • This method offers a robust solution for automated quality control in industrial settings.