Cargando…

Strip Surface Defect Detection Algorithm Based on YOLOv5

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a con...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Han, Yang, Xiuding, Zhou, Bei, Shi, Zhuohao, Zhan, Daohua, Huang, Renbin, Lin, Jian, Wu, Zhiheng, Long, Danfeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10096323/
https://www.ncbi.nlm.nih.gov/pubmed/37049103
http://dx.doi.org/10.3390/ma16072811
_version_ 1785024308746125312
author Wang, Han
Yang, Xiuding
Zhou, Bei
Shi, Zhuohao
Zhan, Daohua
Huang, Renbin
Lin, Jian
Wu, Zhiheng
Long, Danfeng
author_facet Wang, Han
Yang, Xiuding
Zhou, Bei
Shi, Zhuohao
Zhan, Daohua
Huang, Renbin
Lin, Jian
Wu, Zhiheng
Long, Danfeng
author_sort Wang, Han
collection PubMed
description In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.
format Online
Article
Text
id pubmed-10096323
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100963232023-04-13 Strip Surface Defect Detection Algorithm Based on YOLOv5 Wang, Han Yang, Xiuding Zhou, Bei Shi, Zhuohao Zhan, Daohua Huang, Renbin Lin, Jian Wu, Zhiheng Long, Danfeng Materials (Basel) Article In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset. MDPI 2023-03-31 /pmc/articles/PMC10096323/ /pubmed/37049103 http://dx.doi.org/10.3390/ma16072811 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/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/).
spellingShingle Article
Wang, Han
Yang, Xiuding
Zhou, Bei
Shi, Zhuohao
Zhan, Daohua
Huang, Renbin
Lin, Jian
Wu, Zhiheng
Long, Danfeng
Strip Surface Defect Detection Algorithm Based on YOLOv5
title Strip Surface Defect Detection Algorithm Based on YOLOv5
title_full Strip Surface Defect Detection Algorithm Based on YOLOv5
title_fullStr Strip Surface Defect Detection Algorithm Based on YOLOv5
title_full_unstemmed Strip Surface Defect Detection Algorithm Based on YOLOv5
title_short Strip Surface Defect Detection Algorithm Based on YOLOv5
title_sort strip surface defect detection algorithm based on yolov5
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10096323/
https://www.ncbi.nlm.nih.gov/pubmed/37049103
http://dx.doi.org/10.3390/ma16072811
work_keys_str_mv AT wanghan stripsurfacedefectdetectionalgorithmbasedonyolov5
AT yangxiuding stripsurfacedefectdetectionalgorithmbasedonyolov5
AT zhoubei stripsurfacedefectdetectionalgorithmbasedonyolov5
AT shizhuohao stripsurfacedefectdetectionalgorithmbasedonyolov5
AT zhandaohua stripsurfacedefectdetectionalgorithmbasedonyolov5
AT huangrenbin stripsurfacedefectdetectionalgorithmbasedonyolov5
AT linjian stripsurfacedefectdetectionalgorithmbasedonyolov5
AT wuzhiheng stripsurfacedefectdetectionalgorithmbasedonyolov5
AT longdanfeng stripsurfacedefectdetectionalgorithmbasedonyolov5