Cargando…

A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation

Industrial quality detection is one of the important fields in machine vision. Big data analysis, the Internet of Things, edge computing, and other technologies are widely used in industrial quality detection. Studying an industrial detection algorithm that can be organically combined with the Inter...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Ze-Kai, Zhou, Ming-Le, Shao, Rui, Li, Min, Li, Gang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576371/
https://www.ncbi.nlm.nih.gov/pubmed/36262617
http://dx.doi.org/10.1155/2022/6174255
_version_ 1784811510646702080
author Zhang, Ze-Kai
Zhou, Ming-Le
Shao, Rui
Li, Min
Li, Gang
author_facet Zhang, Ze-Kai
Zhou, Ming-Le
Shao, Rui
Li, Min
Li, Gang
author_sort Zhang, Ze-Kai
collection PubMed
description Industrial quality detection is one of the important fields in machine vision. Big data analysis, the Internet of Things, edge computing, and other technologies are widely used in industrial quality detection. Studying an industrial detection algorithm that can be organically combined with the Internet of Things and edge computing is imminent. Deep learning methods in industrial quality detection have been widely proposed recently. However, due to the particularity of industrial scenarios, the existing deep learning-based general object detection methods have shortcomings in industrial applications. This study designs two isomorphic industrial detection models to solve these problems: T-model and S-model. Both proposed models combine swin-transformer with convolution in the backbone and design a residual fusion path. In the neck, this study designs a dual attention module to improve feature fusion. Second, this study presents a knowledge distiller based on the dual attention module to improve the detection accuracy of the lightweight S-model. According to the analysis of the experimental results on four public industrial defect detection datasets, the model in this study is more advantageous in industrial defect detection.
format Online
Article
Text
id pubmed-9576371
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-95763712022-10-18 A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation Zhang, Ze-Kai Zhou, Ming-Le Shao, Rui Li, Min Li, Gang Comput Intell Neurosci Research Article Industrial quality detection is one of the important fields in machine vision. Big data analysis, the Internet of Things, edge computing, and other technologies are widely used in industrial quality detection. Studying an industrial detection algorithm that can be organically combined with the Internet of Things and edge computing is imminent. Deep learning methods in industrial quality detection have been widely proposed recently. However, due to the particularity of industrial scenarios, the existing deep learning-based general object detection methods have shortcomings in industrial applications. This study designs two isomorphic industrial detection models to solve these problems: T-model and S-model. Both proposed models combine swin-transformer with convolution in the backbone and design a residual fusion path. In the neck, this study designs a dual attention module to improve feature fusion. Second, this study presents a knowledge distiller based on the dual attention module to improve the detection accuracy of the lightweight S-model. According to the analysis of the experimental results on four public industrial defect detection datasets, the model in this study is more advantageous in industrial defect detection. Hindawi 2022-10-10 /pmc/articles/PMC9576371/ /pubmed/36262617 http://dx.doi.org/10.1155/2022/6174255 Text en Copyright © 2022 Ze-Kai Zhang et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Zhang, Ze-Kai
Zhou, Ming-Le
Shao, Rui
Li, Min
Li, Gang
A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation
title A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation
title_full A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation
title_fullStr A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation
title_full_unstemmed A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation
title_short A Defect Detection Model for Industrial Products Based on Attention and Knowledge Distillation
title_sort defect detection model for industrial products based on attention and knowledge distillation
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576371/
https://www.ncbi.nlm.nih.gov/pubmed/36262617
http://dx.doi.org/10.1155/2022/6174255
work_keys_str_mv AT zhangzekai adefectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT zhoumingle adefectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT shaorui adefectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT limin adefectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT ligang adefectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT zhangzekai defectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT zhoumingle defectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT shaorui defectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT limin defectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation
AT ligang defectdetectionmodelforindustrialproductsbasedonattentionandknowledgedistillation