An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN
For ensuring the safety and reliability of electronic equipment, it is a necessary task to detect the surface defects of the printed circuit board (PCB). Due to the smallness, complexity and diversity of minor defects of PCB, it is difficult to identify minor defects in PCB with traditional methods....
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Physics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2021.661091/full |
id |
doaj-4a5f8cd7bd314b07b12f7a83d13d9be3 |
---|---|
record_format |
Article |
spelling |
doaj-4a5f8cd7bd314b07b12f7a83d13d9be32021-05-10T08:00:08ZengFrontiers Media S.A.Frontiers in Physics2296-424X2021-05-01910.3389/fphy.2021.661091661091An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCNSiyu Xia0Fan Wang1Fan Wang2Fei Xie3Fei Xie4Lei Huang5Qi Wang6Xu Ling7Xu Ling8School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, ChinaSchool of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, ChinaJiangsu Province 3D Printing Equipment and Manufacturing Key Lab, Nanjing, ChinaSchool of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, ChinaJiangsu Province 3D Printing Equipment and Manufacturing Key Lab, Nanjing, ChinaSchool of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, ChinaSchool of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, ChinaSchool of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, ChinaJiangsu Province 3D Printing Equipment and Manufacturing Key Lab, Nanjing, ChinaFor ensuring the safety and reliability of electronic equipment, it is a necessary task to detect the surface defects of the printed circuit board (PCB). Due to the smallness, complexity and diversity of minor defects of PCB, it is difficult to identify minor defects in PCB with traditional methods. And the target detection method based on deep learning faces the problem of imbalance between foreground and background when detecting minor defects. Therefore, this paper proposes a minor defect detection method on PCB based on FL-RFCN (focal loss and Region-based Fully Convolutional Network) and PHFE (parallel high-definition feature extraction). Firstly, this paper uses the Region-based Fully Convolutional Network(R-FCN) to identify minor defects on the PCB. Secondly, the focal loss is used to solve the problem of data imbalance in neural networks. Thirdly, the parallel high-definition feature extraction algorithm is used to improve the recognition rate of minor defects. In the detection of minor defects on PCB, the ablation experiment proves that the mean Average accuracy (mAP) of the proposed method is increased by 7.4. In comparative experiments, it is found that the mAP of the method proposed in this paper is 12.3 higher than YOLOv3 and 6.7 higher than Faster R-CNN.https://www.frontiersin.org/articles/10.3389/fphy.2021.661091/fullprinted circuit boardminor defectdata enhancementfocal losshigh-definition feature extraction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Siyu Xia Fan Wang Fan Wang Fei Xie Fei Xie Lei Huang Qi Wang Xu Ling Xu Ling |
spellingShingle |
Siyu Xia Fan Wang Fan Wang Fei Xie Fei Xie Lei Huang Qi Wang Xu Ling Xu Ling An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN Frontiers in Physics printed circuit board minor defect data enhancement focal loss high-definition feature extraction |
author_facet |
Siyu Xia Fan Wang Fan Wang Fei Xie Fei Xie Lei Huang Qi Wang Xu Ling Xu Ling |
author_sort |
Siyu Xia |
title |
An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN |
title_short |
An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN |
title_full |
An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN |
title_fullStr |
An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN |
title_full_unstemmed |
An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN |
title_sort |
efficient and robust target detection algorithm for identifying minor defects of printed circuit board based on phfe and fl-rfcn |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Physics |
issn |
2296-424X |
publishDate |
2021-05-01 |
description |
For ensuring the safety and reliability of electronic equipment, it is a necessary task to detect the surface defects of the printed circuit board (PCB). Due to the smallness, complexity and diversity of minor defects of PCB, it is difficult to identify minor defects in PCB with traditional methods. And the target detection method based on deep learning faces the problem of imbalance between foreground and background when detecting minor defects. Therefore, this paper proposes a minor defect detection method on PCB based on FL-RFCN (focal loss and Region-based Fully Convolutional Network) and PHFE (parallel high-definition feature extraction). Firstly, this paper uses the Region-based Fully Convolutional Network(R-FCN) to identify minor defects on the PCB. Secondly, the focal loss is used to solve the problem of data imbalance in neural networks. Thirdly, the parallel high-definition feature extraction algorithm is used to improve the recognition rate of minor defects. In the detection of minor defects on PCB, the ablation experiment proves that the mean Average accuracy (mAP) of the proposed method is increased by 7.4. In comparative experiments, it is found that the mAP of the method proposed in this paper is 12.3 higher than YOLOv3 and 6.7 higher than Faster R-CNN. |
topic |
printed circuit board minor defect data enhancement focal loss high-definition feature extraction |
url |
https://www.frontiersin.org/articles/10.3389/fphy.2021.661091/full |
work_keys_str_mv |
AT siyuxia anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT fanwang anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT fanwang anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT feixie anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT feixie anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT leihuang anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT qiwang anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT xuling anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT xuling anefficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT siyuxia efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT fanwang efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT fanwang efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT feixie efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT feixie efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT leihuang efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT qiwang efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT xuling efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn AT xuling efficientandrobusttargetdetectionalgorithmforidentifyingminordefectsofprintedcircuitboardbasedonphfeandflrfcn |
_version_ |
1721453478797115392 |