YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection

Copper elbows are an important product in industry. They are used to connect pipes for transferring gas, oil, and liquids. Defective copper elbows can lead to serious industrial accidents. In this paper, a novel model named YOT-Net (YOLOv3 combined triplet loss network) is proposed to automatically...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuanqing Xian, Guangjun Liu, Jinfu Fan, Yang Yu, Zhongjie Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	copper elbow defect detection YOLOv3 triplet loss deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/1302b5f0badd4b64b036af395ca8aeb0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1302b5f0badd4b64b036af395ca8aeb0
record_format	dspace
spelling	oai:doaj.org-article:1302b5f0badd4b64b036af395ca8aeb02021-11-11T19:13:32ZYOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection10.3390/s212172601424-8220https://doaj.org/article/1302b5f0badd4b64b036af395ca8aeb02021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7260https://doaj.org/toc/1424-8220Copper elbows are an important product in industry. They are used to connect pipes for transferring gas, oil, and liquids. Defective copper elbows can lead to serious industrial accidents. In this paper, a novel model named YOT-Net (YOLOv3 combined triplet loss network) is proposed to automatically detect defective copper elbows. To increase the defect detection accuracy, triplet loss function is employed in YOT-Net. The triplet loss function is introduced into the loss module of YOT-Net, which utilizes image similarity to enhance feature extraction ability. The proposed method of YOT-Net shows outstanding performance in copper elbow surface defect detection.Yuanqing XianGuangjun LiuJinfu FanYang YuZhongjie WangMDPI AGarticlecopper elbowdefect detectionYOLOv3triplet lossdeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7260, p 7260 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	copper elbow defect detection YOLOv3 triplet loss deep learning Chemical technology TP1-1185
spellingShingle	copper elbow defect detection YOLOv3 triplet loss deep learning Chemical technology TP1-1185 Yuanqing Xian Guangjun Liu Jinfu Fan Yang Yu Zhongjie Wang YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
description	Copper elbows are an important product in industry. They are used to connect pipes for transferring gas, oil, and liquids. Defective copper elbows can lead to serious industrial accidents. In this paper, a novel model named YOT-Net (YOLOv3 combined triplet loss network) is proposed to automatically detect defective copper elbows. To increase the defect detection accuracy, triplet loss function is employed in YOT-Net. The triplet loss function is introduced into the loss module of YOT-Net, which utilizes image similarity to enhance feature extraction ability. The proposed method of YOT-Net shows outstanding performance in copper elbow surface defect detection.
format	article
author	Yuanqing Xian Guangjun Liu Jinfu Fan Yang Yu Zhongjie Wang
author_facet	Yuanqing Xian Guangjun Liu Jinfu Fan Yang Yu Zhongjie Wang
author_sort	Yuanqing Xian
title	YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
title_short	YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
title_full	YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
title_fullStr	YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
title_full_unstemmed	YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
title_sort	yot-net: yolov3 combined triplet loss network for copper elbow surface defect detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1302b5f0badd4b64b036af395ca8aeb0
work_keys_str_mv	AT yuanqingxian yotnetyolov3combinedtripletlossnetworkforcopperelbowsurfacedefectdetection AT guangjunliu yotnetyolov3combinedtripletlossnetworkforcopperelbowsurfacedefectdetection AT jinfufan yotnetyolov3combinedtripletlossnetworkforcopperelbowsurfacedefectdetection AT yangyu yotnetyolov3combinedtripletlossnetworkforcopperelbowsurfacedefectdetection AT zhongjiewang yotnetyolov3combinedtripletlossnetworkforcopperelbowsurfacedefectdetection
_version_	1718431569501224960

YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection

Ejemplares similares