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

Time-independent theoretical framework for stroboscopic nonlinear dynamics based on time-nonlocal response.

Optics express·2026
Same author

Floquet higher-order topological states induced by driving on-site potentials.

Optics express·2026
Same author

Rising lung cancer burden attributable to high fasting plasma glucose in women aged ≥50 years: age-, SDI-, and BRICS-specific patterns from GBD 1990-2021.

Oncology·2026
Same author

Using Deep Learning Models of Gene Regulation to Guide Drug Prioritization.

bioRxiv : the preprint server for biology·2026
Same author

Aroma Characteristics and Volatile Compound Transfer in Jasmine Tea During Scenting.

Foods (Basel, Switzerland)·2026
Same author

Effects of Differentiation <i>Plasmodiophora brassicae</i> Physiological Races on the Rhizosphere Microbial Community Structure of Oilseed Rape.

Microorganisms·2026
Same journal

Application of ephrin-B2 loaded glycol chitosan-silk fibroin hydrogel in the treatment of diabetic refractory wounds.

Scientific reports·2026
Same journal

International expert Delphi consensus on thromboprophylaxis in metabolic and bariatric surgery.

Scientific reports·2026
Same journal

Assessing the cross-region knowledge transfer capability of selected deep learning building vectorization methods in the context of available training datasets.

Scientific reports·2026
Same journal

Feasibility and preliminary effects of outdoor versus indoor cognitive-motor therapy in women with Alzheimer's disease: A randomized single-blind pilot study.

Scientific reports·2026
Same journal

Hallmarks of social action in the vocal turn-taking of wild common marmosets (Callithrix jacchus).

Scientific reports·2026
Same journal

Role and mechanism of AOPPs-induced NOX4-mediated ferroptosis in intervertebral disc degeneration.

Scientific reports·2026
See all related articles

Related Experiment Video

Updated: May 1, 2026

Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

7.5K

MicroDETR for efficient and lightweight PCB defect detection.

Yanru Hu1, Xin Zou2, Xiaoqin Huang2

  • 1School of Physics and Electronic Information Engineering, Ningxia Normal University, Guyuan City, 756000, Ningxia Hui Autonomous Region, China. yixing_166@qq.com.

Scientific Reports
|April 29, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces MicroDETR, a lightweight real-time detection transformer for printed circuit board (PCB) defect detection. MicroDETR significantly improves accuracy and efficiency, especially for micro-scale targets, outperforming existing models.

Keywords:
Adaptive feature aggregationDefect detectionEfficientFusion networkRT-DETR

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

8.7K
Using Synchrotron Radiation Microtomography to Investigate Multi-scale Three-dimensional Microelectronic Packages
08:46

Using Synchrotron Radiation Microtomography to Investigate Multi-scale Three-dimensional Microelectronic Packages

Published on: April 13, 2016

9.6K

Related Experiment Videos

Last Updated: May 1, 2026

Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

7.5K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

8.7K
Using Synchrotron Radiation Microtomography to Investigate Multi-scale Three-dimensional Microelectronic Packages
08:46

Using Synchrotron Radiation Microtomography to Investigate Multi-scale Three-dimensional Microelectronic Packages

Published on: April 13, 2016

9.6K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Industrial Automation

Background:

  • Printed circuit board (PCB) defect detection is challenging due to dense micro-scale targets and complex background textures.
  • Existing models often suffer from parameter redundancy and limited efficiency for real-time applications.

Purpose of the Study:

  • To propose MicroDETR, a novel lightweight real-time detection transformer for enhanced PCB defect detection.
  • To optimize the model for improved accuracy, efficiency, and robustness, particularly for micro-scale defects.

Main Methods:

  • Developed an EfficientBlock backbone using depthwise separable convolution and channel shuffle for feature enhancement and parameter compression.
  • Implemented an Enhanced Multi-Scale Feature Fusion Network (EMSFN) for effective integration of multi-level features.
  • Introduced a Multi-Level Feature Aggregation Module (MLFAM) to reduce complexity and improve micro-target detection.

Main Results:

  • MicroDETR achieved significant improvements in mAP@0.5 (5.1%) and mAP@0.5-0.95 (2.5%), with enhanced recall and precision.
  • The model demonstrated a 15.21% reduction in parameters, 12.11% decrease in computational complexity, and improved processing speed.
  • Exceptional performance on small-scale targets (mAP@0.5 > 77.5%) and superior noise resistance were observed.

Conclusions:

  • MicroDETR offers an optimal balance between accuracy and efficiency for industrial defect detection.
  • The model's real-world applicability is validated through successful deployment on edge devices.
  • Publicly available code and models facilitate further research and application in PCB defect detection.