.png){kind=icon}
Return
Multiscale Convolution-Based Probabilistic Classification for Detecting Bare PCB Defects
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2022.3229708.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Feature extraction
Convolution
Uncertainty
Probabilistic logic
Production
Learning systems
Kernel
Bare printed circuit board (PCB)
computer vision
convolution network
defect detection
multiscale classification
Journal
IF:
5.9
Papers:
2.0W
Citations:
5.8W
Organization
Cited Papers
An Insulator Defect Detection Model in Aerial Images Based on Multiscale Feature Pyramid Network
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSaveAssociation Between Levothyroxine Treatment and Thyroid-Related Symptoms Among Adults Aged 80 Years and Older With Subclinical Hypothyroidism.png)
JAMA
OAAI
JAMAIF0
OAAIShareSave
View more