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: Jun 29, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K

High-Frequency Workpiece Image Recognition Model Integrating Multi-Level Network Structure.

Yang Ou1, Chenglong Sun2, Rong Yuan1

  • 1School of Mechanical Engineering, Chengdu University, Chengdu 610106, China.

Sensors (Basel, Switzerland)
|March 28, 2024
PubMed
Summary
This summary is machine-generated.

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

Cell-Resolved Mass Spectrometry Imaging Integrated with Isotope Tracing Elucidates Macrophage Polarization-Specific Metabolic Reprogramming.

Analytical chemistry·2026
Same author

Ecophysiological Characteristics of High-Photosynthetic-Efficiency Rice Varieties and Their Environmental Regulation.

Physiologia plantarum·2026
Same author

Enhanced aerodynamic and mechanical performance of double-rotor wind turbines via a one-way fluid-structure interaction analysis.

PloS one·2026
Same author

Self-propelled nanozyme motors for targeted therapy of radiation cystitis by disrupting the inflammation-cfDNA vicious cycle.

Journal of nanobiotechnology·2026
Same author

Qi-Blood Harmony Formula ameliorates myocardial infarction in coronary atherosclerotic heart disease by reversing circRNA-mediated inhibition of angiogenesis via EIF4A3 stabilization.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Dynamic Chemical Profiling of <i>Lonicera japonica</i> Flos During the Maceration and Decoction Processes Integrating UPLC-MS and Molecular Networking.

Foods (Basel, Switzerland)·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

A new ML-EfficientNet-B1 model enhances high-frequency workpiece recognition by combining global and local image features. This approach improves accuracy to 98.3%, overcoming challenges in complex textures and illumination variations.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Industrial Automation

Background:

  • High-frequency workpiece recognition is challenging due to complex intra-class textures and subtle inter-class differences.
  • Existing models struggle with low recognition rates for these challenging image characteristics.

Purpose of the Study:

  • To develop a novel and robust high-frequency workpiece image recognition model.
  • To improve recognition accuracy and adaptability to illumination changes.

Main Methods:

  • Proposed a Multi-Level EfficientNet-B1 (ML-EfficientNet-B1) model integrating EfficientNet-B1.
  • Incorporated a lightweight mixed attention module for global feature extraction with illumination robustness.
  • Utilized a weakly supervised area detection module for local feature extraction and a branch fusion module for combining results.
Keywords:
deep learninghybrid attentionimage recognitionnetwork structure

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
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

530

Related Experiment Videos

Last Updated: Jun 29, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
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

530

Main Results:

  • The ML-EfficientNet-B1 model demonstrated superior adaptability to illumination variations compared to other models.
  • Achieved a significant improvement in high-frequency workpiece recognition performance.
  • Attained a final recognition accuracy of 98.3%.

Conclusions:

  • The proposed ML-EfficientNet-B1 model effectively addresses the limitations of existing methods for high-frequency workpiece recognition.
  • The integration of global and local feature extraction enhances recognition robustness and accuracy.
  • This model offers a promising solution for industrial applications requiring precise workpiece identification.