Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components

This paper describes the application of Semantic Networks for the detection of defects in images of metallic manufactured components in a situation where the number of available samples of defects is small, which is rather common in real practical environments. In order to overcome this shortage of...

Descripción completa

Detalles Bibliográficos
Autores: Saiz, Fátima A., Alfaro, Garazi, Barandiaran, Iñigo, Graña Romay, Manuel María
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/52643
Acceso en línea:http://hdl.handle.net/10810/52643
Access Level:acceso abierto
Palabra clave:defect segmentation
data augmentation
generative adversarial networks
industrial manufacturing
quality inspection
photometric stereo
id ES_0b9738ea785a87dd674746163b80fa7e
oai_identifier_str oai:addi.ehu.eus:10810/52643
network_acronym_str ES
network_name_str España
repository_id_str
spelling Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing ComponentsSaiz, Fátima A.Alfaro, GaraziBarandiaran, IñigoGraña Romay, Manuel Maríadefect segmentationdata augmentationgenerative adversarial networksindustrial manufacturingquality inspectionphotometric stereoThis paper describes the application of Semantic Networks for the detection of defects in images of metallic manufactured components in a situation where the number of available samples of defects is small, which is rather common in real practical environments. In order to overcome this shortage of data, the common approach is to use conventional data augmentation techniques. We resort to Generative Adversarial Networks (GANs) that have shown the capability to generate highly convincing samples of a specific class as a result of a game between a discriminator and a generator module. Here, we apply the GANs to generate samples of images of metallic manufactured components with specific defects, in order to improve training of Semantic Networks (specifically DeepLabV3+ and Pyramid Attention Network (PAN) networks) carrying out the defect detection and segmentation. Our process carries out the generation of defect images using the StyleGAN2 with the DiffAugment method, followed by a conventional data augmentation over the entire enriched dataset, achieving a large balanced dataset that allows robust training of the Semantic Network. We demonstrate the approach on a private dataset generated for an industrial client, where images are captured by an ad-hoc photometric-stereo image acquisition system, and a public dataset, the Northeastern University surface defect database (NEU). The proposed approach achieves an improvement of 7% and 6% in an intersection over union (IoU) measure of detection performance on each dataset over the conventional data augmentation.MDPI2021202120212021info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10810/52643reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoIngléshttps://www.mdpi.com/2076-3417/11/14/6368info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/3.0/es/© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).oai:addi.ehu.eus:10810/526432026-06-18T09:23:17Z
dc.title.none.fl_str_mv Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
title Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
spellingShingle Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
Saiz, Fátima A.
defect segmentation
data augmentation
generative adversarial networks
industrial manufacturing
quality inspection
photometric stereo
title_short Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
title_full Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
title_fullStr Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
title_full_unstemmed Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
title_sort Generative Adversarial Networks to Improve the Robustness of Visual Defect Segmentation by Semantic Networks in Manufacturing Components
dc.creator.none.fl_str_mv Saiz, Fátima A.
Alfaro, Garazi
Barandiaran, Iñigo
Graña Romay, Manuel María
author Saiz, Fátima A.
author_facet Saiz, Fátima A.
Alfaro, Garazi
Barandiaran, Iñigo
Graña Romay, Manuel María
author_role author
author2 Alfaro, Garazi
Barandiaran, Iñigo
Graña Romay, Manuel María
author2_role author
author
author
dc.subject.none.fl_str_mv defect segmentation
data augmentation
generative adversarial networks
industrial manufacturing
quality inspection
photometric stereo
topic defect segmentation
data augmentation
generative adversarial networks
industrial manufacturing
quality inspection
photometric stereo
description This paper describes the application of Semantic Networks for the detection of defects in images of metallic manufactured components in a situation where the number of available samples of defects is small, which is rather common in real practical environments. In order to overcome this shortage of data, the common approach is to use conventional data augmentation techniques. We resort to Generative Adversarial Networks (GANs) that have shown the capability to generate highly convincing samples of a specific class as a result of a game between a discriminator and a generator module. Here, we apply the GANs to generate samples of images of metallic manufactured components with specific defects, in order to improve training of Semantic Networks (specifically DeepLabV3+ and Pyramid Attention Network (PAN) networks) carrying out the defect detection and segmentation. Our process carries out the generation of defect images using the StyleGAN2 with the DiffAugment method, followed by a conventional data augmentation over the entire enriched dataset, achieving a large balanced dataset that allows robust training of the Semantic Network. We demonstrate the approach on a private dataset generated for an industrial client, where images are captured by an ad-hoc photometric-stereo image acquisition system, and a public dataset, the Northeastern University surface defect database (NEU). The proposed approach achieves an improvement of 7% and 6% in an intersection over union (IoU) measure of detection performance on each dataset over the conventional data augmentation.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10810/52643
url http://hdl.handle.net/10810/52643
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://www.mdpi.com/2076-3417/11/14/6368
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/3.0/es/
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Addi. Archivo Digital para la Docencia y la Investigación
instname:Universidad del País Vasco
instname_str Universidad del País Vasco
reponame_str Addi. Archivo Digital para la Docencia y la Investigación
collection Addi. Archivo Digital para la Docencia y la Investigación
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403235925622784
score 15,300719

Similares en LA Referencia