skip to main content
10.1145/3445815.3445853acmotherconferencesArticle/Chapter ViewAbstractPublication PagescsaiConference Proceedingsconference-collections
research-article

An Improved PCB Defect Detector Based on Feature Pyramid Networks

Published: 17 March 2021 Publication History

Abstract

Aiming at the problem of false alarm in PCB defect detection in the automatic optical inspection process, many researchers have proposed their methods, but most of them only classify the single defect in single image, and there are multiple defects and multiple categories in single image. In this paper, a real PCB data set consisting of 1540 images generated by AOI is introduced for the detection and classification task. In addition, we propose an improved PCB defect detector based on feature pyramid networks. The detector combines Faster R-CNN and FPN as the infrastructure, and has been adjusted and improved, mainly including the following three innovations: 1) SE module is inserted into the feature extraction backbone network resnet-101, which improves the expression ability of network. 2) An enhanced bottom-up structure is introduced to enhance the whole feature level by using accurate low-level positioning signals. 3) ROI Align is used instead of RoI Pooling to reduce the impact of dislocation on small object defect detection. The experimental results show that, compared with the mainstream object detection network, the proposed method achieves better accuracy, reaching 96.3% mAP, and has better performance for defect detection and classification.

References

[1]
Deng, Y.S., Luo, A.C.,Dai, M.J.:‘Building an Automatic Defect Verification System Using Deep Neural Network for PCB Defect Classification’, International Conference on Frontiers of Signal Processing (ICFSP), Poitiers, France, September 2018,pp. 145–149
[2]
Hagi H, Iwahori Y, Fukui S, Defect Classification of Electronic Circuit Board Using SVM based on Random Sampling[J]. Procedia Computer Science, 2014, 35:1210-1218.
[3]
Shiina T, Iwahori Y, Takada Y, Kijsirikul B, Bhuyan M, (2018) Reducing misclassification of true defects in defect classification of electronic board. Computer and Information Science 719: 77.
[4]
Peng, W., Chang, L., Mengyuan, L., Yunlong, G., & Hong, L. . CNN-based reference comparison method for classifying bare PCB defects. 2018(16), 1528-1533.
[5]
Ghosh B, Bhuyan M K, Sasmal P, Defect Classification of Printed Circuit Boards based on Transfer Learning[C]// 2018 IEEE Applied Signal Processing Conference (ASPCON). IEEE, 2019.
[6]
Sikka S, Sikka K, Bhuyan M K, Pseudo vs. True Defect Classification in Printed Circuits Boards using Wavelet Features[J]. Computer ence, 2013.
[7]
Nakagawa T, Iwahori Y, Bhuyan M K. Reduction of Defect Misclassification of Electronic Board Using Multiple SVM Classifiers [J]. 2016.
[8]
Yuji Iwahori,Yohei Takada,Tokiko Shiina,Yoshinori Adachi,M.K. Bhuyan,Boonserm Kijsirikul. Defect Classification of Electronic Board Using Dense SIFT and CNN [J]. Procedia Computer Science, 2018,126.
[9]
Yuk, Eun & Park, Seung & Park, Cheong-Sool & Baek, Jun-Geol. (2018). Feature-Learning-Based Printed Circuit Board Inspection via Speeded-Up Robust Features and Random Forest. Applied Sciences. 8. 932. 10.3390/app8060932.
[10]
Yohei Takada, Tokiko Shiina, Hiroyasu Usami, Yuji Iwahori and M. K. Bhuyan (2017) “Defect Detection and Classification of Electronic Circuit Boards Using Keypoint Extraction and CNN Features.” PATTERNS 2017 113–116.
[11]
Jin Y. Convolutional neural network-based multi-label classification of PCB defects [J]. The Journal of Engineering, 2018, 2018.
[12]
Shiina, Tokiko & Iwahori, Yuji & Kijsirikul, Boonserm. (2018). Defect Classification of Electronic Circuit Board Using Multi-Input Convolutional Neural Network. International Journal of Computer & Software Engineering. 3. 10.15344/2456-4451/2018/137.
[13]
T. Lin, P. Dollar, R. B. Girshick, K. He, B. Hariharan, and ´ S. J. Belongie. Feature pyramid networks for object detection. In CVPR, 2017.
[14]
Hu J, Shen L, Albanie S, Squeeze-and-Excitation Networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, PP (99).
[15]
Liu S, Qi L, Qin H, Path Aggregation Network for Instance Segmentation [J]. 2018.
[16]
K. He, G. Gkioxari, P. Dollar, and R. B. Girshick. Mask ´ R-CNN. In ICCV, 2017.
[17]
S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS, 2015.
[18]
Redmon, J. and A. Farhadi, Yolov3: An incremental improvement. ArXiv preprint arXiv: 1804.02767,2018.
[19]
Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection [J]. 2020.
[20]
Lin T Y, Goyal P, Girshick R, Focal Loss for Dense Object Detection [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, PP (99):2999-3007.

Cited By

View all
  • (2025)A Comparative Analysis of Printed Circuit Boards Defect Detection Leveraging Deep Learning ApproachesHighlights in Science, Engineering and Technology10.54097/11xrk596124(102-107)Online publication date: 18-Feb-2025
  • (2024)Attentive context and semantic enhancement mechanism for printed circuit board defect detection with two-stage and multi-stage object detectorsScientific Reports10.1038/s41598-024-69207-814:1Online publication date: 5-Aug-2024
  • (2023)Conditional TransGAN‐Based Data Augmentation for PCB Electronic Component InspectionComputational Intelligence and Neuroscience10.1155/2023/20242372023:1Online publication date: 10-Jan-2023
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
CSAI '20: Proceedings of the 2020 4th International Conference on Computer Science and Artificial Intelligence
December 2020
294 pages
ISBN:9781450388436
DOI:10.1145/3445815
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 March 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Automatic Optical Inspection
  2. False Alarm
  3. PCB Defect Detector
  4. Printed Circuit Board

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

CSAI 2020

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)27
  • Downloads (Last 6 weeks)0
Reflects downloads up to 25 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)A Comparative Analysis of Printed Circuit Boards Defect Detection Leveraging Deep Learning ApproachesHighlights in Science, Engineering and Technology10.54097/11xrk596124(102-107)Online publication date: 18-Feb-2025
  • (2024)Attentive context and semantic enhancement mechanism for printed circuit board defect detection with two-stage and multi-stage object detectorsScientific Reports10.1038/s41598-024-69207-814:1Online publication date: 5-Aug-2024
  • (2023)Conditional TransGAN‐Based Data Augmentation for PCB Electronic Component InspectionComputational Intelligence and Neuroscience10.1155/2023/20242372023:1Online publication date: 10-Jan-2023
  • (2023)PCB surface defect detection based on improved YOLOv7-tiny2023 5th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)10.1109/MLBDBI60823.2023.10482094(334-337)Online publication date: 15-Dec-2023
  • (2023)A Comprehensive Review of Deep Learning-Based PCB Defect DetectionIEEE Access10.1109/ACCESS.2023.333956111(139017-139038)Online publication date: 2023
  • (2023)Toward Optimal Defect Detection in Assembled Printed Circuit Boards Under Adverse ConditionsIEEE Access10.1109/ACCESS.2023.333014211(127119-127131)Online publication date: 2023
  • (2022)Cross-Domain Few-Shot Learning Approach for Lithium-Ion Battery Surface Defects Classification Using an Improved Siamese NetworkIEEE Sensors Journal10.1109/JSEN.2022.316133122:12(11847-11856)Online publication date: 15-Jun-2022
  • (2022)A lightweight and efficient model for surface tiny defect detectionApplied Intelligence10.1007/s10489-022-03633-x53:6(6344-6353)Online publication date: 8-Jul-2022
  • (2021)PCB Classification using Convolutional Neural Network2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N)10.1109/ICAC3N53548.2021.9725695(986-990)Online publication date: 17-Dec-2021

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media