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

Search research articles

Related Experiment Video

Updated: Jul 15, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images.

Daohua Zhan^1,2, Renbin Huang^1,2, Kunran Yi^1,2

¹State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, China.

|September 28, 2023

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

Design and Vision-Based Calibration of a Five-Axis Precision Dispensing Machine.

Micromachines·2026

Same author

A High-Precision Multi-Beam Optical Measurement Method for Cylindrical Surface Profile.

Micromachines·2023

Same author

ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding.

Micromachines·2023

Same author

A Lightweight Method for Detecting IC Wire Bonding Defects in X-ray Images.

Micromachines·2023

Same author

Strip Surface Defect Detection Algorithm Based on YOLOv5.

Materials (Basel, Switzerland)·2023

Same author

Research on the Mechanism of Multi-Domain Coupling Centrifugal Electrostatic Blowing Flying Deposition.

Micromachines·2022

This study introduces YOLO-CSS, a new method for detecting defects in wire bonding X-ray images. It improves accuracy and speed for complex industrial inspections.

Area of Science:

Computer Vision
Artificial Intelligence
Materials Science

Background:

Defect detection in wire bonding X-ray images faces challenges from complex backgrounds, small defects, and varied defect types.
Existing methods struggle to achieve high accuracy and efficiency for these demanding industrial inspection tasks.

Purpose of the Study:

To develop an advanced defect detection method for wire bonding X-ray images.
To enhance the accuracy and efficiency of identifying diverse defects in challenging imaging conditions.

Main Methods:

A novel convolutional neural network (CNN)-based method, YOLO-CSS, was proposed.
It features a new extraction network for semantic features from gradient information and a self-adaptive weighted multi-scale feature fusion module (SMA).

Keywords:

X-ray images YOLO-CSS convolutional neural network wire bonding defects

More Related Videos

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 15, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Skip connections were integrated to preserve feature integrity.

Main Results:

The YOLO-CSS algorithm achieved high performance on a wire bonding X-ray defect dataset, with mAP@0.5 of 97.3% and mAP@0.5-0.95 of 72.1%.
It outperformed existing YOLO series algorithms in detection accuracy.
The method demonstrated advantages in model size and detection speed, balancing accuracy and efficiency.

Conclusions:

YOLO-CSS effectively addresses the challenges in wire bonding X-ray defect detection.
The proposed method offers a superior balance of accuracy, speed, and model efficiency for industrial applications.