Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs

Products’ quality inspection is an important stage in every production route, in which the quality of the produced goods is estimated and compared with the desired specifications. With traditional inspection, the process rely on manual methods that generates various costs and large time consu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ahmed Najah, Faiz F. Mustafa, Wisam S. Hacham
Formato:	article
Lenguaje:	EN
Publicado:	Al-Khwarizmi College of Engineering – University of Baghdad 2021
Materias:	Chemical engineering TP155-156 Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/d11bb6d6637943acbc9e4081d9b86fa5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d11bb6d6637943acbc9e4081d9b86fa5
record_format	dspace
spelling	oai:doaj.org-article:d11bb6d6637943acbc9e4081d9b86fa52021-12-02T17:29:35ZBuilding a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs10.22153/kej.2021.12.0011818-11712312-0789https://doaj.org/article/d11bb6d6637943acbc9e4081d9b86fa52021-03-01T00:00:00Zhttps://alkej.uobaghdad.edu.iq/index.php/alkej/article/view/733https://doaj.org/toc/1818-1171https://doaj.org/toc/2312-0789 Products’ quality inspection is an important stage in every production route, in which the quality of the produced goods is estimated and compared with the desired specifications. With traditional inspection, the process rely on manual methods that generates various costs and large time consumption. On the contrary, today’s inspection systems that use modern techniques like computer vision, are more accurate and efficient. However, the amount of work needed to build a computer vision system based on classic techniques is relatively large, due to the issue of manually selecting and extracting features from digital images, which also produces labor costs for the system engineers. In this research, we present an adopted approach based on convolutional neural networks to design a system for quality inspection with high level of accuracy and low cost. The system is designed using transfer learning to transfer layers from a previously trained model and a fully connected neural network to classify the product’s condition into healthy or damaged. Helical gears were used as the inspected object and three cameras with differing resolutions were used to evaluate the system with colored and grayscale images. Experimental results showed high accuracy levels with colored images and even higher accuracies with grayscale images at every resolution, emphasizing the ability to build an inspection system at low costs, ease of construction and automatic extraction of image features. Ahmed NajahFaiz F. MustafaWisam S. HachamAl-Khwarizmi College of Engineering – University of BaghdadarticleChemical engineeringTP155-156Engineering (General). Civil engineering (General)TA1-2040ENAl-Khawarizmi Engineering Journal, Vol 17, Iss 1 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Chemical engineering TP155-156 Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Chemical engineering TP155-156 Engineering (General). Civil engineering (General) TA1-2040 Ahmed Najah Faiz F. Mustafa Wisam S. Hacham Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs
description	Products’ quality inspection is an important stage in every production route, in which the quality of the produced goods is estimated and compared with the desired specifications. With traditional inspection, the process rely on manual methods that generates various costs and large time consumption. On the contrary, today’s inspection systems that use modern techniques like computer vision, are more accurate and efficient. However, the amount of work needed to build a computer vision system based on classic techniques is relatively large, due to the issue of manually selecting and extracting features from digital images, which also produces labor costs for the system engineers. In this research, we present an adopted approach based on convolutional neural networks to design a system for quality inspection with high level of accuracy and low cost. The system is designed using transfer learning to transfer layers from a previously trained model and a fully connected neural network to classify the product’s condition into healthy or damaged. Helical gears were used as the inspected object and three cameras with differing resolutions were used to evaluate the system with colored and grayscale images. Experimental results showed high accuracy levels with colored images and even higher accuracies with grayscale images at every resolution, emphasizing the ability to build an inspection system at low costs, ease of construction and automatic extraction of image features.
format	article
author	Ahmed Najah Faiz F. Mustafa Wisam S. Hacham
author_facet	Ahmed Najah Faiz F. Mustafa Wisam S. Hacham
author_sort	Ahmed Najah
title	Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs
title_short	Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs
title_full	Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs
title_fullStr	Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs
title_full_unstemmed	Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs
title_sort	building a high accuracy transfer learning-based quality inspection system at low costs
publisher	Al-Khwarizmi College of Engineering – University of Baghdad
publishDate	2021
url	https://doaj.org/article/d11bb6d6637943acbc9e4081d9b86fa5
work_keys_str_mv	AT ahmednajah buildingahighaccuracytransferlearningbasedqualityinspectionsystematlowcosts AT faizfmustafa buildingahighaccuracytransferlearningbasedqualityinspectionsystematlowcosts AT wisamshacham buildingahighaccuracytransferlearningbasedqualityinspectionsystematlowcosts
_version_	1718380756398505984

Building a High Accuracy Transfer Learning-Based Quality Inspection System at Low Costs

Ejemplares similares