Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs

Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Zhu, Liying [verfasserIn] Wang, Sen [verfasserIn] Chen, Mingfang [verfasserIn] Shen, Aiping [verfasserIn] Li, Xuangang [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2024

Schlagwörter:	PCB defect detection Object detection EFFNet Auxiliary supervision BCE-LRM

Anmerkung:	© The Author(s) 2024

Übergeordnetes Werk:	Enthalten in: Complex & intelligent systems - Springer International Publishing, 2015, 10(2024), 6 vom: 24. Juli, Seite 7591-7604
Übergeordnetes Werk:	volume:10 ; year:2024 ; number:6 ; day:24 ; month:07 ; pages:7591-7604

Links:	Volltext

DOI / URN:	10.1007/s40747-024-01554-5

Katalog-ID:	SPR05782522X

Internformat


LEADER	01000naa a22002652 4500
001	SPR05782522X
003	DE-627
005	20241017064815.0
007	cr uuu---uuuuu
008	241017s2024 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1007/s40747-024-01554-5 \|2 doi
035			\|a (DE-627)SPR05782522X
035			\|a (SPR)s40747-024-01554-5-e
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
082	0	4	\|a 004 \|q VZ
100	1		\|a Zhu, Liying \|e verfasserin \|4 aut
245	1	0	\|a Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
264		1	\|c 2024
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
500			\|a © The Author(s) 2024
520			\|a Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS).
650		4	\|a PCB defect detection \|7 (dpeaa)DE-He213
650		4	\|a Object detection \|7 (dpeaa)DE-He213
650		4	\|a EFFNet \|7 (dpeaa)DE-He213
650		4	\|a Auxiliary supervision \|7 (dpeaa)DE-He213
650		4	\|a BCE-LRM \|7 (dpeaa)DE-He213
700	1		\|a Wang, Sen \|e verfasserin \|0 (orcid)0000-0003-1259-8030 \|4 aut
700	1		\|a Chen, Mingfang \|e verfasserin \|4 aut
700	1		\|a Shen, Aiping \|e verfasserin \|4 aut
700	1		\|a Li, Xuangang \|e verfasserin \|4 aut
773	0	8	\|i Enthalten in \|t Complex & intelligent systems \|d Springer International Publishing, 2015 \|g 10(2024), 6 vom: 24. Juli, Seite 7591-7604 \|w (DE-627)835589269 \|w (DE-600)2834740-7 \|x 2198-6053 \|7 nnns
773	1	8	\|g volume:10 \|g year:2024 \|g number:6 \|g day:24 \|g month:07 \|g pages:7591-7604
856	4	0	\|u https://dx.doi.org/10.1007/s40747-024-01554-5 \|m X:SPRINGER \|x Resolving-System \|z kostenfrei \|3 Volltext
912			\|a SYSFLAG_0
912			\|a GBV_SPRINGER
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_72
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2050
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4326
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 10 \|j 2024 \|e 6 \|b 24 \|c 07 \|h 7591-7604

Indexfelder

author_variant	l z lz s w sw m c mc a s as x l xl
matchkey_str	article:21986053:2024----::noprtnlntidticmlxakrudfriulufc
hierarchy_sort_str	2024
publishDate	2024
allfields	10.1007/s40747-024-01554-5 doi (DE-627)SPR05782522X (SPR)s40747-024-01554-5-e DE-627 ger DE-627 rakwb eng 004 VZ Zhu, Liying verfasserin aut Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2024 Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). PCB defect detection (dpeaa)DE-He213 Object detection (dpeaa)DE-He213 EFFNet (dpeaa)DE-He213 Auxiliary supervision (dpeaa)DE-He213 BCE-LRM (dpeaa)DE-He213 Wang, Sen verfasserin (orcid)0000-0003-1259-8030 aut Chen, Mingfang verfasserin aut Shen, Aiping verfasserin aut Li, Xuangang verfasserin aut Enthalten in Complex & intelligent systems Springer International Publishing, 2015 10(2024), 6 vom: 24. Juli, Seite 7591-7604 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604 https://dx.doi.org/10.1007/s40747-024-01554-5 X:SPRINGER Resolving-System kostenfrei Volltext SYSFLAG_0 GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_72 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2050 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2024 6 24 07 7591-7604
spelling	10.1007/s40747-024-01554-5 doi (DE-627)SPR05782522X (SPR)s40747-024-01554-5-e DE-627 ger DE-627 rakwb eng 004 VZ Zhu, Liying verfasserin aut Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2024 Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). PCB defect detection (dpeaa)DE-He213 Object detection (dpeaa)DE-He213 EFFNet (dpeaa)DE-He213 Auxiliary supervision (dpeaa)DE-He213 BCE-LRM (dpeaa)DE-He213 Wang, Sen verfasserin (orcid)0000-0003-1259-8030 aut Chen, Mingfang verfasserin aut Shen, Aiping verfasserin aut Li, Xuangang verfasserin aut Enthalten in Complex & intelligent systems Springer International Publishing, 2015 10(2024), 6 vom: 24. Juli, Seite 7591-7604 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604 https://dx.doi.org/10.1007/s40747-024-01554-5 X:SPRINGER Resolving-System kostenfrei Volltext SYSFLAG_0 GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_72 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2050 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2024 6 24 07 7591-7604
allfields_unstemmed	10.1007/s40747-024-01554-5 doi (DE-627)SPR05782522X (SPR)s40747-024-01554-5-e DE-627 ger DE-627 rakwb eng 004 VZ Zhu, Liying verfasserin aut Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2024 Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). PCB defect detection (dpeaa)DE-He213 Object detection (dpeaa)DE-He213 EFFNet (dpeaa)DE-He213 Auxiliary supervision (dpeaa)DE-He213 BCE-LRM (dpeaa)DE-He213 Wang, Sen verfasserin (orcid)0000-0003-1259-8030 aut Chen, Mingfang verfasserin aut Shen, Aiping verfasserin aut Li, Xuangang verfasserin aut Enthalten in Complex & intelligent systems Springer International Publishing, 2015 10(2024), 6 vom: 24. Juli, Seite 7591-7604 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604 https://dx.doi.org/10.1007/s40747-024-01554-5 X:SPRINGER Resolving-System kostenfrei Volltext SYSFLAG_0 GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_72 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2050 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2024 6 24 07 7591-7604
allfieldsGer	10.1007/s40747-024-01554-5 doi (DE-627)SPR05782522X (SPR)s40747-024-01554-5-e DE-627 ger DE-627 rakwb eng 004 VZ Zhu, Liying verfasserin aut Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2024 Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). PCB defect detection (dpeaa)DE-He213 Object detection (dpeaa)DE-He213 EFFNet (dpeaa)DE-He213 Auxiliary supervision (dpeaa)DE-He213 BCE-LRM (dpeaa)DE-He213 Wang, Sen verfasserin (orcid)0000-0003-1259-8030 aut Chen, Mingfang verfasserin aut Shen, Aiping verfasserin aut Li, Xuangang verfasserin aut Enthalten in Complex & intelligent systems Springer International Publishing, 2015 10(2024), 6 vom: 24. Juli, Seite 7591-7604 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604 https://dx.doi.org/10.1007/s40747-024-01554-5 X:SPRINGER Resolving-System kostenfrei Volltext SYSFLAG_0 GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_72 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2050 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2024 6 24 07 7591-7604
allfieldsSound	10.1007/s40747-024-01554-5 doi (DE-627)SPR05782522X (SPR)s40747-024-01554-5-e DE-627 ger DE-627 rakwb eng 004 VZ Zhu, Liying verfasserin aut Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2024 Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). PCB defect detection (dpeaa)DE-He213 Object detection (dpeaa)DE-He213 EFFNet (dpeaa)DE-He213 Auxiliary supervision (dpeaa)DE-He213 BCE-LRM (dpeaa)DE-He213 Wang, Sen verfasserin (orcid)0000-0003-1259-8030 aut Chen, Mingfang verfasserin aut Shen, Aiping verfasserin aut Li, Xuangang verfasserin aut Enthalten in Complex & intelligent systems Springer International Publishing, 2015 10(2024), 6 vom: 24. Juli, Seite 7591-7604 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604 https://dx.doi.org/10.1007/s40747-024-01554-5 X:SPRINGER Resolving-System kostenfrei Volltext SYSFLAG_0 GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_72 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2050 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2024 6 24 07 7591-7604
language	English
source	Enthalten in Complex & intelligent systems 10(2024), 6 vom: 24. Juli, Seite 7591-7604 volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604
sourceStr	Enthalten in Complex & intelligent systems 10(2024), 6 vom: 24. Juli, Seite 7591-7604 volume:10 year:2024 number:6 day:24 month:07 pages:7591-7604
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	PCB defect detection Object detection EFFNet Auxiliary supervision BCE-LRM
dewey-raw	004
isfreeaccess_bool	true
container_title	Complex & intelligent systems
authorswithroles_txt_mv	Zhu, Liying @@aut@@ Wang, Sen @@aut@@ Chen, Mingfang @@aut@@ Shen, Aiping @@aut@@ Li, Xuangang @@aut@@
publishDateDaySort_date	2024-07-24T00:00:00Z
hierarchy_top_id	835589269
dewey-sort	14
id	SPR05782522X
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR05782522X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20241017064815.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">241017s2024 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s40747-024-01554-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR05782522X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s40747-024-01554-5-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhu, Liying</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2024</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2024</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS).</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">PCB defect detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">EFFNet</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Auxiliary supervision</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">BCE-LRM</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Sen</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-1259-8030</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Mingfang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shen, Aiping</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Xuangang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Complex & intelligent systems</subfield><subfield code="d">Springer International Publishing, 2015</subfield><subfield code="g">10(2024), 6 vom: 24. Juli, Seite 7591-7604</subfield><subfield code="w">(DE-627)835589269</subfield><subfield code="w">(DE-600)2834740-7</subfield><subfield code="x">2198-6053</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:10</subfield><subfield code="g">year:2024</subfield><subfield code="g">number:6</subfield><subfield code="g">day:24</subfield><subfield code="g">month:07</subfield><subfield code="g">pages:7591-7604</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s40747-024-01554-5</subfield><subfield code="m">X:SPRINGER</subfield><subfield code="x">Resolving-System</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_0</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_72</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">10</subfield><subfield code="j">2024</subfield><subfield code="e">6</subfield><subfield code="b">24</subfield><subfield code="c">07</subfield><subfield code="h">7591-7604</subfield></datafield></record></collection>
author	Zhu, Liying
spellingShingle	Zhu, Liying ddc 004 misc PCB defect detection misc Object detection misc EFFNet misc Auxiliary supervision misc BCE-LRM Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
authorStr	Zhu, Liying
ppnlink_with_tag_str_mv	@@773@@(DE-627)835589269
format	electronic Article
dewey-ones	004 - Data processing & computer science
delete_txt_mv	keep
author_role	aut aut aut aut aut
collection	springer
remote_str	true
illustrated	Not Illustrated
issn	2198-6053
topic_title	004 VZ Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs PCB defect detection (dpeaa)DE-He213 Object detection (dpeaa)DE-He213 EFFNet (dpeaa)DE-He213 Auxiliary supervision (dpeaa)DE-He213 BCE-LRM (dpeaa)DE-He213
topic	ddc 004 misc PCB defect detection misc Object detection misc EFFNet misc Auxiliary supervision misc BCE-LRM
topic_unstemmed	ddc 004 misc PCB defect detection misc Object detection misc EFFNet misc Auxiliary supervision misc BCE-LRM
topic_browse	ddc 004 misc PCB defect detection misc Object detection misc EFFNet misc Auxiliary supervision misc BCE-LRM
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Complex & intelligent systems
hierarchy_parent_id	835589269
dewey-tens	000 - Computer science, knowledge & systems
hierarchy_top_title	Complex & intelligent systems
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)835589269 (DE-600)2834740-7
title	Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
ctrlnum	(DE-627)SPR05782522X (SPR)s40747-024-01554-5-e
title_full	Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
author_sort	Zhu, Liying
journal	Complex & intelligent systems
journalStr	Complex & intelligent systems
lang_code	eng
isOA_bool	true
dewey-hundreds	000 - Computer science, information & general works
recordtype	marc
publishDateSort	2024
contenttype_str_mv	txt
container_start_page	7591
author_browse	Zhu, Liying Wang, Sen Chen, Mingfang Shen, Aiping Li, Xuangang
container_volume	10
class	004 VZ
format_se	Elektronische Aufsätze
author-letter	Zhu, Liying
doi_str_mv	10.1007/s40747-024-01554-5
normlink	(ORCID)0000-0003-1259-8030
normlink_prefix_str_mv	(orcid)0000-0003-1259-8030
dewey-full	004
author2-role	verfasserin
title_sort	incorporating long-tail data in complex backgrounds for visual surface defect detection in pcbs
title_auth	Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
abstract	Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). © The Author(s) 2024
abstractGer	Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). © The Author(s) 2024
abstract_unstemmed	Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS). © The Author(s) 2024
collection_details	SYSFLAG_0 GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_72 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2050 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	6
title_short	Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
url	https://dx.doi.org/10.1007/s40747-024-01554-5
remote_bool	true
author2	Wang, Sen Chen, Mingfang Shen, Aiping Li, Xuangang
author2Str	Wang, Sen Chen, Mingfang Shen, Aiping Li, Xuangang
ppnlink	835589269
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.1007/s40747-024-01554-5
up_date	2024-10-17T04:51:08.129Z
_version_	1813135405217742848
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR05782522X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20241017064815.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">241017s2024 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s40747-024-01554-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR05782522X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s40747-024-01554-5-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhu, Liying</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2024</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2024</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS).</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">PCB defect detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">EFFNet</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Auxiliary supervision</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">BCE-LRM</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Sen</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-1259-8030</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Mingfang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shen, Aiping</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Xuangang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Complex & intelligent systems</subfield><subfield code="d">Springer International Publishing, 2015</subfield><subfield code="g">10(2024), 6 vom: 24. Juli, Seite 7591-7604</subfield><subfield code="w">(DE-627)835589269</subfield><subfield code="w">(DE-600)2834740-7</subfield><subfield code="x">2198-6053</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:10</subfield><subfield code="g">year:2024</subfield><subfield code="g">number:6</subfield><subfield code="g">day:24</subfield><subfield code="g">month:07</subfield><subfield code="g">pages:7591-7604</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s40747-024-01554-5</subfield><subfield code="m">X:SPRINGER</subfield><subfield code="x">Resolving-System</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_0</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_72</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">10</subfield><subfield code="j">2024</subfield><subfield code="e">6</subfield><subfield code="b">24</subfield><subfield code="c">07</subfield><subfield code="h">7591-7604</subfield></datafield></record></collection>
score	7.398529

Nicht das Richtige dabei?

Schreiben Sie uns!

Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?