2021
DOI: 10.1007/s42835-021-00885-4
|View full text |Cite
|
Sign up to set email alerts
|

Character Identification for Integrated Circuit Components on Printed Circuit Boards Using Deep Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
0
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 23 publications
0
0
0
Order By: Relevance
“… Lu et al (2018) proved the effectiveness of fused features in defect classification problems, but their proposed algorithm cannot detect specific defect positions on the PCB surface. Jia & Liu (2022) improved the LeNet-5 network model for PCB character defect detection by changing the layer depth to examine the impact of different network architectures on model efficiency and adding a combination classifier in the fully connected layer to enhance the feature expression performance. However, this proposed method does not reduce the need for human intervention during the training process, and it is still a significant challenge to study the segmentation of overlapping character clusters.…”
Section: Introductionmentioning
confidence: 99%
“… Lu et al (2018) proved the effectiveness of fused features in defect classification problems, but their proposed algorithm cannot detect specific defect positions on the PCB surface. Jia & Liu (2022) improved the LeNet-5 network model for PCB character defect detection by changing the layer depth to examine the impact of different network architectures on model efficiency and adding a combination classifier in the fully connected layer to enhance the feature expression performance. However, this proposed method does not reduce the need for human intervention during the training process, and it is still a significant challenge to study the segmentation of overlapping character clusters.…”
Section: Introductionmentioning
confidence: 99%