Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning
As the size of components mounted on printed circuit boards (PCBs) decreases, defect detection becomes more important. The first step in an inspection involves recognizing and inspecting characters printed on parts attached to the PCB. In addition, since industrial fields that produce PCBs can chang...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/9/2921 |
id |
doaj-9eddcb5a6bbf4643af819e75cfa12468 |
---|---|
record_format |
Article |
spelling |
doaj-9eddcb5a6bbf4643af819e75cfa124682021-04-21T23:06:52ZengMDPI AGSensors1424-82202021-04-01212921292110.3390/s21092921Character Recognition of Components Mounted on Printed Circuit Board Using Deep LearningSumyung Gang0Ndayishimiye Fabrice1Daewon Chung2Joonjae Lee3Department of Computer Engineering, Keimyung University, Daegu 42601, KoreaDepartment of Computer Engineering, Keimyung University, Daegu 42601, KoreaFaculty of Basic Sciences, Keimyung University, Daegu 42601, KoreaFaculty of Computer Engineering, Keimyung University, Daegu 42601, KoreaAs the size of components mounted on printed circuit boards (PCBs) decreases, defect detection becomes more important. The first step in an inspection involves recognizing and inspecting characters printed on parts attached to the PCB. In addition, since industrial fields that produce PCBs can change very rapidly, the style of the collected data may vary between collection sites and collection periods. Therefore, flexible learning data that can respond to all fields and time periods are needed. In this paper, large amounts of character data on PCB components were obtained and analyzed in depth. In addition, we proposed a method of recognizing characters by constructing a dataset that was robust with various fonts and environmental changes using a large amount of data. Moreover, a coreset capable of evaluating an effective deep learning model and a base set using n-pick sampling capable of responding to a continuously increasing dataset were proposed. Existing original data and the EfficientNet B0 model showed an accuracy of 97.741%. However, the accuracy of our proposed model was increased to 98.274% for the coreset of 8000 images per class. In particular, the accuracy was 98.921% for the base set with only 1900 images per class.https://www.mdpi.com/1424-8220/21/9/2921PCB inspectionoptical character recognition (OCR)deep learningcoreset |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sumyung Gang Ndayishimiye Fabrice Daewon Chung Joonjae Lee |
spellingShingle |
Sumyung Gang Ndayishimiye Fabrice Daewon Chung Joonjae Lee Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning Sensors PCB inspection optical character recognition (OCR) deep learning coreset |
author_facet |
Sumyung Gang Ndayishimiye Fabrice Daewon Chung Joonjae Lee |
author_sort |
Sumyung Gang |
title |
Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning |
title_short |
Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning |
title_full |
Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning |
title_fullStr |
Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning |
title_full_unstemmed |
Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning |
title_sort |
character recognition of components mounted on printed circuit board using deep learning |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-04-01 |
description |
As the size of components mounted on printed circuit boards (PCBs) decreases, defect detection becomes more important. The first step in an inspection involves recognizing and inspecting characters printed on parts attached to the PCB. In addition, since industrial fields that produce PCBs can change very rapidly, the style of the collected data may vary between collection sites and collection periods. Therefore, flexible learning data that can respond to all fields and time periods are needed. In this paper, large amounts of character data on PCB components were obtained and analyzed in depth. In addition, we proposed a method of recognizing characters by constructing a dataset that was robust with various fonts and environmental changes using a large amount of data. Moreover, a coreset capable of evaluating an effective deep learning model and a base set using n-pick sampling capable of responding to a continuously increasing dataset were proposed. Existing original data and the EfficientNet B0 model showed an accuracy of 97.741%. However, the accuracy of our proposed model was increased to 98.274% for the coreset of 8000 images per class. In particular, the accuracy was 98.921% for the base set with only 1900 images per class. |
topic |
PCB inspection optical character recognition (OCR) deep learning coreset |
url |
https://www.mdpi.com/1424-8220/21/9/2921 |
work_keys_str_mv |
AT sumyunggang characterrecognitionofcomponentsmountedonprintedcircuitboardusingdeeplearning AT ndayishimiyefabrice characterrecognitionofcomponentsmountedonprintedcircuitboardusingdeeplearning AT daewonchung characterrecognitionofcomponentsmountedonprintedcircuitboardusingdeeplearning AT joonjaelee characterrecognitionofcomponentsmountedonprintedcircuitboardusingdeeplearning |
_version_ |
1721515305228828672 |