Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network

The growth of electronic devices increases the demands of printed circuit boards (PCB) productions in the electronic industries. This leads to the rise in the quantity of PCB productions every day. Consequently, automated visual inspection becomes an essential system to be equipped in any producti...

Full description

Bibliographic Details
Main Author: Cheong, Leong Kean
Format: Monograph
Language:English
Published: Universiti Sains Malaysia 2018
Subjects:
Online Access:http://eprints.usm.my/53328/
http://eprints.usm.my/53328/1/Defect%20And%20Components%20Recognition%20In%20Printed%20Circuit%20Boards%20Using%20Convolution%20Neural%20Network_Cheong%20Leong%20Kean_E3_2018.pdf
_version_ 1848882497696301056
author Cheong, Leong Kean
author_facet Cheong, Leong Kean
author_sort Cheong, Leong Kean
building USM Institutional Repository
collection Online Access
description The growth of electronic devices increases the demands of printed circuit boards (PCB) productions in the electronic industries. This leads to the rise in the quantity of PCB productions every day. Consequently, automated visual inspection becomes an essential system to be equipped in any production line to ensure the quality of the PCB produced which brings us to the aim of this project, building an automated components recognition system for PCB using CNN. In addition to that, localization on the defects of the PCB components will also be performed. In the first stage, a simple CNN-based component recognition classifier will be developed. Since training a CNN from scratch is expensive, transfer learning with ImageNet pre-trained models is performed instead. Pre-trained models such as VGG16, DenseNet169 and InceptionV3 are used to investigate which model suits the best for components recognition. Using transfer learning with VGG-16, the best result achieved is 99% accuracy with the capability of recognizing up to 25 different components. Following that, object localization is performed using faster region-based convolutional neural network (R-CNN). Multiple experiments have been performed to determine the optimum method and training parameters to achieve a system that is able to localize defects on the PCB with high accuracy and precision. The best mean average precision (mAP) achieved for the defects localization system is 96.54%.
first_indexed 2025-11-15T18:35:52Z
format Monograph
id usm-53328
institution Universiti Sains Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T18:35:52Z
publishDate 2018
publisher Universiti Sains Malaysia
recordtype eprints
repository_type Digital Repository
spelling usm-533282022-07-13T00:44:15Z http://eprints.usm.my/53328/ Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network Cheong, Leong Kean T Technology TK Electrical Engineering. Electronics. Nuclear Engineering The growth of electronic devices increases the demands of printed circuit boards (PCB) productions in the electronic industries. This leads to the rise in the quantity of PCB productions every day. Consequently, automated visual inspection becomes an essential system to be equipped in any production line to ensure the quality of the PCB produced which brings us to the aim of this project, building an automated components recognition system for PCB using CNN. In addition to that, localization on the defects of the PCB components will also be performed. In the first stage, a simple CNN-based component recognition classifier will be developed. Since training a CNN from scratch is expensive, transfer learning with ImageNet pre-trained models is performed instead. Pre-trained models such as VGG16, DenseNet169 and InceptionV3 are used to investigate which model suits the best for components recognition. Using transfer learning with VGG-16, the best result achieved is 99% accuracy with the capability of recognizing up to 25 different components. Following that, object localization is performed using faster region-based convolutional neural network (R-CNN). Multiple experiments have been performed to determine the optimum method and training parameters to achieve a system that is able to localize defects on the PCB with high accuracy and precision. The best mean average precision (mAP) achieved for the defects localization system is 96.54%. Universiti Sains Malaysia 2018-06-01 Monograph NonPeerReviewed application/pdf en http://eprints.usm.my/53328/1/Defect%20And%20Components%20Recognition%20In%20Printed%20Circuit%20Boards%20Using%20Convolution%20Neural%20Network_Cheong%20Leong%20Kean_E3_2018.pdf Cheong, Leong Kean (2018) Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network. Project Report. Universiti Sains Malaysia, Pusat Pengajian Kejuruteraan Elektrik dan Elektronik. (Submitted)
spellingShingle T Technology
TK Electrical Engineering. Electronics. Nuclear Engineering
Cheong, Leong Kean
Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network
title Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network
title_full Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network
title_fullStr Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network
title_full_unstemmed Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network
title_short Defect And Components Recognition In Printed Circuit Boards Using Convolution Neural Network
title_sort defect and components recognition in printed circuit boards using convolution neural network
topic T Technology
TK Electrical Engineering. Electronics. Nuclear Engineering
url http://eprints.usm.my/53328/
http://eprints.usm.my/53328/1/Defect%20And%20Components%20Recognition%20In%20Printed%20Circuit%20Boards%20Using%20Convolution%20Neural%20Network_Cheong%20Leong%20Kean_E3_2018.pdf