Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network

Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network

The detection of defects in a product is one of required production process for quality control. Currently, the quality control process of metal screws uses many manpower for manual inspection. Hence, this study about to implement faster region-based convolutional neural network (faster R-CNN) to de...

Full description

Bibliographic Details
Published in:Smart Innovation, Systems and Technologies
Main Author: Patar M.N.A.A.; Ayub M.A.; Zainal N.A.; Rosly M.A.; Lee H.; Hanafusa A.
Format: Conference paper
Language:English
Published: Springer Science and Business Media Deutschland GmbH 2022
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121811038&doi=10.1007%2f978-981-16-6482-3_58&partnerID=40&md5=4886afb77d46a8dd8b91abb10632bd07
id 2-s2.0-85121811038
spelling 2-s2.0-85121811038
Patar M.N.A.A.; Ayub M.A.; Zainal N.A.; Rosly M.A.; Lee H.; Hanafusa A.
Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
2022
Smart Innovation, Systems and Technologies
265

10.1007/978-981-16-6482-3_58
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121811038&doi=10.1007%2f978-981-16-6482-3_58&partnerID=40&md5=4886afb77d46a8dd8b91abb10632bd07
The detection of defects in a product is one of required production process for quality control. Currently, the quality control process of metal screws uses many manpower for manual inspection. Hence, this study about to implement faster region-based convolutional neural network (faster R-CNN) to detect the micro-defects on metal screw surfaces. The defects of surface damage, stripped screw, and dirty surface screw considered in this research. Raspberry Pi 3 with a camera module is used for image acquisition of the metal screws in determining various kinds of defects. The image is also acquired to be used for the training of the faster R-CNN. A testing is carried out to test the performance of the model. The experiment outcome shows that the detection accuracy of the model is 98.8%. The model also shows superiority in this project detection method compared with the traditional template-matching method and single-shot detector (SSD) model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Springer Science and Business Media Deutschland GmbH
21903018
English
Conference paper
author Patar M.N.A.A.; Ayub M.A.; Zainal N.A.; Rosly M.A.; Lee H.; Hanafusa A.
spellingShingle Patar M.N.A.A.; Ayub M.A.; Zainal N.A.; Rosly M.A.; Lee H.; Hanafusa A.
Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
author_facet Patar M.N.A.A.; Ayub M.A.; Zainal N.A.; Rosly M.A.; Lee H.; Hanafusa A.
author_sort Patar M.N.A.A.; Ayub M.A.; Zainal N.A.; Rosly M.A.; Lee H.; Hanafusa A.
title Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
title_short Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
title_full Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
title_fullStr Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
title_full_unstemmed Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
title_sort Detection of Micro-defects on Metal Screw Surfaces Based on Faster Region-Based Convolutional Neural Network
publishDate 2022
container_title Smart Innovation, Systems and Technologies
container_volume 265
container_issue
doi_str_mv 10.1007/978-981-16-6482-3_58
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121811038&doi=10.1007%2f978-981-16-6482-3_58&partnerID=40&md5=4886afb77d46a8dd8b91abb10632bd07
description The detection of defects in a product is one of required production process for quality control. Currently, the quality control process of metal screws uses many manpower for manual inspection. Hence, this study about to implement faster region-based convolutional neural network (faster R-CNN) to detect the micro-defects on metal screw surfaces. The defects of surface damage, stripped screw, and dirty surface screw considered in this research. Raspberry Pi 3 with a camera module is used for image acquisition of the metal screws in determining various kinds of defects. The image is also acquired to be used for the training of the faster R-CNN. A testing is carried out to test the performance of the model. The experiment outcome shows that the detection accuracy of the model is 98.8%. The model also shows superiority in this project detection method compared with the traditional template-matching method and single-shot detector (SSD) model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
publisher Springer Science and Business Media Deutschland GmbH
issn 21903018
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1809678158633369600

Similar Items