Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing

This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dongbeom Ko, Sungjoo Kang, Hyunsuk Kim, Wongok Lee, Yousuk Bae, Jeongmin Park
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	anomaly detection fault segmentation DeeplabV3+ depth image segmentation tire manufacturing Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/f566b8493874411788ce35d4ea748587
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f566b8493874411788ce35d4ea748587
record_format	dspace
spelling	oai:doaj.org-article:f566b8493874411788ce35d4ea7485872021-11-11T15:23:52ZAnomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing10.3390/app1121103762076-3417https://doaj.org/article/f566b8493874411788ce35d4ea7485872021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10376https://doaj.org/toc/2076-3417This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial Revolution and the development of deep learning require deep learning–based problem solving in various fields. Accordingly, various research efforts use deep learning technology to detect errors, such as product defects and diseases, in depth images. However, a depth image expressed in grayscale has limited information, compared with a three-channel image with potential colors, shapes, and brightness. In addition, in the case of tires, despite the same defect, they often have different sizes and shapes, making it difficult to train deep learning. Therefore, in this paper, the four-step process of (1) image input, (2) highlight image generation, (3) image stacking, and (4) image training is applied to a deep learning segmentation model that can detect atypical defect data. Defect detection aims to detect vent spews that occur during tire manufacturing. We compare the training results of applying the process proposed in this paper and the general training result for experiment and evaluation. For evaluation, we use intersection of union (IoU), which compares the pixel area where the actual error is located in the depth image and the pixel area of the error inferred by the deep learning network. The results of the experiment confirmed that the proposed methodology improved the mean IoU by more than 7% and the IoU for the vent spew error by more than 10%, compared to the general method. In addition, the time it takes for the mean IoU to remain stable at 60% is reduced by 80%. The experiments and results prove that the methodology proposed in this paper can train efficiently without losing the information of the original depth data.Dongbeom KoSungjoo KangHyunsuk KimWongok LeeYousuk BaeJeongmin ParkMDPI AGarticleanomaly detectionfault segmentationDeeplabV3+depth image segmentationtire manufacturingTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10376, p 10376 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	anomaly detection fault segmentation DeeplabV3+ depth image segmentation tire manufacturing Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	anomaly detection fault segmentation DeeplabV3+ depth image segmentation tire manufacturing Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Dongbeom Ko Sungjoo Kang Hyunsuk Kim Wongok Lee Yousuk Bae Jeongmin Park Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing
description	This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial Revolution and the development of deep learning require deep learning–based problem solving in various fields. Accordingly, various research efforts use deep learning technology to detect errors, such as product defects and diseases, in depth images. However, a depth image expressed in grayscale has limited information, compared with a three-channel image with potential colors, shapes, and brightness. In addition, in the case of tires, despite the same defect, they often have different sizes and shapes, making it difficult to train deep learning. Therefore, in this paper, the four-step process of (1) image input, (2) highlight image generation, (3) image stacking, and (4) image training is applied to a deep learning segmentation model that can detect atypical defect data. Defect detection aims to detect vent spews that occur during tire manufacturing. We compare the training results of applying the process proposed in this paper and the general training result for experiment and evaluation. For evaluation, we use intersection of union (IoU), which compares the pixel area where the actual error is located in the depth image and the pixel area of the error inferred by the deep learning network. The results of the experiment confirmed that the proposed methodology improved the mean IoU by more than 7% and the IoU for the vent spew error by more than 10%, compared to the general method. In addition, the time it takes for the mean IoU to remain stable at 60% is reduced by 80%. The experiments and results prove that the methodology proposed in this paper can train efficiently without losing the information of the original depth data.
format	article
author	Dongbeom Ko Sungjoo Kang Hyunsuk Kim Wongok Lee Yousuk Bae Jeongmin Park
author_facet	Dongbeom Ko Sungjoo Kang Hyunsuk Kim Wongok Lee Yousuk Bae Jeongmin Park
author_sort	Dongbeom Ko
title	Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing
title_short	Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing
title_full	Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing
title_fullStr	Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing
title_full_unstemmed	Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing
title_sort	anomaly segmentation based on depth image for quality inspection processes in tire manufacturing
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f566b8493874411788ce35d4ea748587
work_keys_str_mv	AT dongbeomko anomalysegmentationbasedondepthimageforqualityinspectionprocessesintiremanufacturing AT sungjookang anomalysegmentationbasedondepthimageforqualityinspectionprocessesintiremanufacturing AT hyunsukkim anomalysegmentationbasedondepthimageforqualityinspectionprocessesintiremanufacturing AT wongoklee anomalysegmentationbasedondepthimageforqualityinspectionprocessesintiremanufacturing AT yousukbae anomalysegmentationbasedondepthimageforqualityinspectionprocessesintiremanufacturing AT jeongminpark anomalysegmentationbasedondepthimageforqualityinspectionprocessesintiremanufacturing
_version_	1718435405578108928

Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing

Ejemplares similares