Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a ti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ivan Kuric, Jaromír Klarák, Milan Sága, Miroslav Císar, Adrián Hajdučík, Dariusz Wiecek
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	tire inspection deep learning unsupervised learning polynomial regression laser sensor defect detection Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/84cf6c3e3cb34491b94582f38c7a3de8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:84cf6c3e3cb34491b94582f38c7a3de8
record_format	dspace
spelling	oai:doaj.org-article:84cf6c3e3cb34491b94582f38c7a3de82021-11-11T19:05:28ZAnalysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning10.3390/s212170731424-8220https://doaj.org/article/84cf6c3e3cb34491b94582f38c7a3de82021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7073https://doaj.org/toc/1424-8220At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.Ivan KuricJaromír KlarákMilan SágaMiroslav CísarAdrián HajdučíkDariusz WiecekMDPI AGarticletire inspectiondeep learningunsupervised learningpolynomial regressionlaser sensordefect detectionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7073, p 7073 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	tire inspection deep learning unsupervised learning polynomial regression laser sensor defect detection Chemical technology TP1-1185
spellingShingle	tire inspection deep learning unsupervised learning polynomial regression laser sensor defect detection Chemical technology TP1-1185 Ivan Kuric Jaromír Klarák Milan Sága Miroslav Císar Adrián Hajdučík Dariusz Wiecek Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
description	At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.
format	article
author	Ivan Kuric Jaromír Klarák Milan Sága Miroslav Císar Adrián Hajdučík Dariusz Wiecek
author_facet	Ivan Kuric Jaromír Klarák Milan Sága Miroslav Císar Adrián Hajdučík Dariusz Wiecek
author_sort	Ivan Kuric
title	Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
title_short	Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
title_full	Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
title_fullStr	Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
title_full_unstemmed	Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
title_sort	analysis of the possibilities of tire-defect inspection based on unsupervised learning and deep learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/84cf6c3e3cb34491b94582f38c7a3de8
work_keys_str_mv	AT ivankuric analysisofthepossibilitiesoftiredefectinspectionbasedonunsupervisedlearninganddeeplearning AT jaromirklarak analysisofthepossibilitiesoftiredefectinspectionbasedonunsupervisedlearninganddeeplearning AT milansaga analysisofthepossibilitiesoftiredefectinspectionbasedonunsupervisedlearninganddeeplearning AT miroslavcisar analysisofthepossibilitiesoftiredefectinspectionbasedonunsupervisedlearninganddeeplearning AT adrianhajducik analysisofthepossibilitiesoftiredefectinspectionbasedonunsupervisedlearninganddeeplearning AT dariuszwiecek analysisofthepossibilitiesoftiredefectinspectionbasedonunsupervisedlearninganddeeplearning
_version_	1718431656922054656

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

Ejemplares similares