Multiscale Convolution-Based Probabilistic Classification for Detecting Bare PCB Defects

Defect detection is an essential part of quality management for bare printed circuit board (PCB) production. Existing vision-based methods are not effective in detecting PCB defects when uncertainty exists. This article proposes a multiscale convolution-based detection methodology to classify bare P...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement 2023, Vol.72, p.1-8
Main Authors: Lei, Lei, Li, Han-Xiong, Yang, Hai-Dong
Format: Article
Language:English
Subjects:
Bare printed circuit board (PCB)
Circuit boards
Classification
computer vision
Convolution
convolution network
defect detection
Defects
Feature extraction
Kernel
Learning systems
multiscale classification
Printed circuits
Probabilistic logic
Production
Production methods
Quality management
Statistical analysis
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Defect detection is an essential part of quality management for bare printed circuit board (PCB) production. Existing vision-based methods are not effective in detecting PCB defects when uncertainty exists. This article proposes a multiscale convolution-based detection methodology to classify bare PCB defects under uncertainty. First, a novel window-based loss function is designed to tackle the inter-class imbalance and uncertainty. Then, a multiscale convolution network is constructed to process the defects with intra-class variance, and large scale extraction features are fused on the small scale to guide the extraction process. After that, the classification probability is extracted and assembled into a multiscale probability matrix, on which entropy-based probabilistic decisions are integrated for the final decision. Finally, experimental studies indicate that the proposed methodology can achieve satisfactory detection performance and demonstrate visual interpretability compared to baseline methods.
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2022.3229708