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

ProCoS: Degradation-Robust Manipulation Localization for Special Equipment Inspection Images.

Sensors (Basel, Switzerland)·2026
Same author

Tracking the trajectory of mangrove dynamics in the Zambezi Delta, East Africa's largest river Delta.

Journal of environmental management·2026
Same author

Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework.

Sensors (Basel, Switzerland)·2025
Same author

An Improved Generative Adversarial Network-Based and U-Shaped Transformer Method for Glass Curtain Crack Deblurring Using UAVs.

Sensors (Basel, Switzerland)·2024
Same author

Pressure vessel-oriented visual inspection method based on deep learning.

PloS one·2022
Same author

Characterization of the complete mitochondrial genome of blacktip shark <i>Carcharhinus limbatus</i> (Carcharhiniformes: Carcharhinidae).

Mitochondrial DNA. Part B, Resources·2022

Related Experiment Video

Updated: Nov 18, 2025

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

3.1K

Fast semantic segmentation method for machine vision inspection based on a fewer-parameters atrous convolution neural

Jian Huang1, Liu Guixiong1, Binyuan He1

  • 1School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, Guangdong Province, China.

Plos One
|February 10, 2021
PubMed
Summary

This study introduces an optimized deep learning model for machine vision inspection, significantly reducing processing time for online semantic segmentation in complex backgrounds. The enhanced model enables faster, parameter-efficient visual detection, suitable for mobile devices.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

650
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

1.4K

Related Experiment Videos

Last Updated: Nov 18, 2025

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

3.1K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

650
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

1.4K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Machine vision is crucial for intelligent manufacturing, particularly in quality inspection and precision production lines.
  • Online semantic segmentation under complex backgrounds presents a significant challenge in current machine vision applications.

Purpose of the Study:

  • To develop an optimized deep learning model for online semantic segmentation in machine vision inspection.
  • To improve the efficiency and parameter optimization of atrous convolution architectures for complex background segmentation.

Main Methods:

  • Utilized Atrous Spatial Pyramid Pooling (ASPP) and Residual Network (ResNet) as base architectures.
  • Proposed five modified ResNet residual building blocks to enhance image feature utilization.
  • Implemented fewer-parameters optimization for atrous convolution architecture.

Main Results:

  • Achieved a significant decrease in segmentation time (Tseg) from 719 ms to 296 ms (58.8% reduction).
  • Maintained high accuracy with only a minor decrease in intersection-over-union (IoU) from 86.7% to 86.6%.
  • Demonstrated applicability through successful segmentation of Chinese Yuan (CNY) currency.

Conclusions:

  • The proposed semantic segmentation model effectively reduces detection time while ensuring accuracy.
  • The fewer-parameters optimization makes neural network detection feasible on mobile terminals.
  • The method offers a significant advancement for real-time visual detection in intelligent manufacturing.