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

Evaluation of red CdTe and near infrared CdHgTe quantum dots by fluorescent imaging.

Journal of nanoscience and nanotechnology·2008

Same author

Exploring feasibility of multicolored CdTe quantum dots for in vitro and in vivo fluorescent imaging.

Journal of nanoscience and nanotechnology·2008

Same author

[Effects of Dahuang Zhechong Pill on expressions of tissue inhibitor of metalloproteinase-1 and plasminogen activator inhibitor-1 in rats with glomerulosclerosis].

Zhong xi yi jie he xue bao = Journal of Chinese integrative medicine·2008

Same author

[Construction and expression of a fusion protein containing extracellular domain of human Delta-like1 and Fc fragment of human IgG1 in the Pichia pastoris].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2008

Same author

[Preparation and characterization of the monoclonal antibodies to PTD-bcr/abl].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2008

Same author

Prostaglandin F2alpha induces the normoxic activation of the hypoxia-inducible factor-1 transcription factor in differentiating 3T3-L1 preadipocytes: Potential role in the regulation of adipogenesis.

Journal of cellular biochemistry·2008

Search research articles

Related Experiment Video

Updated: Jul 8, 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 of industrial components based on vision.

Zhendong Chen^1,2, Xuefeng Feng³, Li Liu^1,2

¹College of Information Science and Engineering, Xinjiang University, Urumqi, 830046, China.

Scientific Reports

|December 13, 2023

Summary

This study introduces an improved YOLOv5 model for high-precision industrial surface defect detection, significantly reducing missed and false detections. The enhanced model achieves superior accuracy in identifying subtle defects, improving overall industrial safety.

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Published on: January 6, 2023

Related Experiment Videos

Last Updated: Jul 8, 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

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Published on: January 6, 2023

Area of Science:

Computer Vision
Machine Learning
Industrial Quality Control

Background:

Industrial component surface defects pose safety risks.
Tiny defects with similar backgrounds cause low detection accuracy (missed/false detections).

Purpose of the Study:

To develop a high-precision surface defect detection model for industrial components.
To improve upon the YOLOv5 algorithm for enhanced accuracy and reliability.

Main Methods:

Proposed SPPFKCSPC module for improved multi-scale feature extraction and fusion.
Integrated SPPFKCSPC with C3 module in the backbone for enhanced feature expression and receptive field.
Embedded Coordinate Attention mechanism (CA) and improved bounding box regression to EIOU loss function.

Main Results:

Achieved 88.3% mean average accuracy (mAP) on the NEU-DET dataset, a 7.2% improvement.
Reached 97.5% mAP on the PV-Multi-Defect dataset, a 1.5% improvement.
Demonstrated significant improvements in detection accuracy and overall network performance.

Conclusions:

The proposed YOLOv5-based model effectively enhances surface defect detection precision.
The innovative modules and techniques improve feature extraction, localization, and recognition.
The model offers a robust solution for industrial component surface defect identification.