Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Quantitative proteomic analysis was performed to evaluate the protein expression levels in the ovaries of goats with different litter sizes.

BMC genomics·2026

Same author

Differences in Peripheral Blood Gene Expression of Xinjiang Brown Cattle with Varying Somatic Cell Counts.

Biology·2026

Same author

Population Structure Analysis and Candidate Gene Screening for Twinning Trait in Simmental Cattle.

Animals : an open access journal from MDPI·2026

Same author

Key regulators of lactation performance in Xinjiang Brown cattle and Chinese Holstein cattle unraveled by multi-omics integration.

Frontiers in veterinary science·2026

Same author

CircRNA <i>AIDA</i> Regulates Development of Bovine Myoblast via Binding miR-29a.

Cells·2026

Same author

Investigating the Regulatory Mechanisms and Prognostic Significance of miR-941 Targeting the Nrf2/Keap1 Pathway in Elderly Ischemic Stroke Patients.

Cellular and molecular neurobiology·2026

Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026

Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026

Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026

Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026

Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026

Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 9, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Surface defect detection method for electronic panels based on double branching and decoupling head structure.

Le Wang¹, Xixia Huang¹, Zhangjing Zheng¹

¹Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai, People's Republic of China.

|February 24, 2023

Summary

This summary is machine-generated.

This study introduces a novel deep learning object detection network for identifying electronic panel surface defects. The new method improves accuracy for multi-scale, irregular defects by decoupling regression and classification tasks.

More Related Videos

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Published on: June 3, 2015

Related Experiment Videos

Last Updated: Aug 9, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Published on: June 3, 2015

Area of Science:

Computer Vision
Machine Learning
Electronic Manufacturing

Background:

Surface defects in electronic panels are common and impact product quality.
Manual and traditional detection methods are costly and inaccurate.
Existing deep learning object detection networks struggle with electronic panel surface defects due to unique defect characteristics and coupled regression/classification tasks.

Purpose of the Study:

To address the limitations of current methods for electronic panel surface defect detection.
To propose a novel supervised object detection network tailored for this specific application.
To improve the accuracy and efficiency of defect detection in electronic panel production.

Main Methods:

Designed a supervised object detection network with a double-branch structure for prediction box generation.
Implemented a detection head strategy that decouples regression and classification tasks.
Validated the network on a custom dataset of electronic panel surface defects.

Main Results:

The proposed network achieved an average accuracy of 78.897% across 64 defect categories.
Comparative and ablation experiments demonstrated the effectiveness of the new method.
The decoupled approach successfully mitigated the conflict between regression and classification tasks.

Conclusions:

The novel supervised object detection network is effective for electronic panel surface defect detection.
Decoupling regression and classification tasks is crucial for improving detection performance.
The proposed method offers a more accurate and efficient solution compared to existing techniques.