EW-YOLOv7: A Lightweight and Effective Detection Model for Small Defects in Electrowetting Display

In order to overcome the shortcomings of existing electrowetting display defect detection models in terms of computational complexity, structural complexity, detection speed, and detection accuracy, this article proposes an improved YOLOv7-based electrowetting display defect detection model. The mod...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Processes 2023-07, Vol.11 (7), p.2037
Hauptverfasser: Zheng, Zihan, Chen, Ningxia, Wu, Jianhao, Xv, Zhixuan, Liu, Shuangyin, Luo, Zhijie
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 7
container_start_page 2037
container_title Processes
container_volume 11
creator Zheng, Zihan
Chen, Ningxia
Wu, Jianhao
Xv, Zhixuan
Liu, Shuangyin
Luo, Zhijie
description In order to overcome the shortcomings of existing electrowetting display defect detection models in terms of computational complexity, structural complexity, detection speed, and detection accuracy, this article proposes an improved YOLOv7-based electrowetting display defect detection model. The model effectively optimizes the detection performance of display defects, especially small target defects, by integrating GhostNetV2 modules, Acmix attention mechanisms, and NGWD (Normalized Gaussian Wasserstein Distance) Loss. At the same time, it reduces the parameter size of the network model and improves the inference efficiency of the network. This article evaluates the performance of an improved model using a self-constructed electrowetting display defect dataset. The experimental results show that the proposed improved model achieves an average detection rate (mAP) of 89.5% and an average inference time of 35.9 ms. Compared to the original network, the number of parameters and computational costs are reduced by 19.2% and 64.3%, respectively. Compared with current state-of-the-art detection network models, the proposed EW-YOLOv7 exhibits superior performance in detecting electrowetting display defects. This model helps to solve the problem of defect detection in industrial production of electrowetting display and assists the research team in quickly identifying the causes and locations of defects.
doi_str_mv 10.3390/pr11072037
format Article
fullrecord <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2843105724</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A759190681</galeid><sourcerecordid>A759190681</sourcerecordid><originalsourceid>FETCH-LOGICAL-c334t-16b358b309111b207790f0a002c204d6c58e2378ffd0f3bbbe16b9c5008dae463</originalsourceid><addsrcrecordid>eNpNUN9LwzAQDqLgmHvxLwj4JnRekrZpfRvb_AGVPaiITyVtk5nRNTXJNvbfmzJB7-Du4-777o5D6JrAlLEc7npLCHAKjJ-hEaWURzkn_PwfvkQT5zYQLCcsS9IRqpYf0eeqWO35PZ7hQq-__EEOEYuuwUulZO31XuKF9AMyHX4xjWyxMha_bkXbhs7AcVh3eNkGZM1Beq-7NV5o17fieIUulGidnPzmMXp_WL7Nn6Ji9fg8nxVRzVjsI5JWLMkqFk4jpKLAeQ4KBACtKcRNWieZpIxnSjWgWFVVMijyOgHIGiHjlI3RzWlub833TjpfbszOdmFlSbOYEUg4jQNremKtRStL3SnjraiDN3Kra9NJpUN9xpOc5JBmJAhuT4LaGuesVGVv9VbYY0mgHP5e_v2d_QCdUHLj</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2843105724</pqid></control><display><type>article</type><title>EW-YOLOv7: A Lightweight and Effective Detection Model for Small Defects in Electrowetting Display</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Zheng, Zihan ; Chen, Ningxia ; Wu, Jianhao ; Xv, Zhixuan ; Liu, Shuangyin ; Luo, Zhijie</creator><creatorcontrib>Zheng, Zihan ; Chen, Ningxia ; Wu, Jianhao ; Xv, Zhixuan ; Liu, Shuangyin ; Luo, Zhijie</creatorcontrib><description>In order to overcome the shortcomings of existing electrowetting display defect detection models in terms of computational complexity, structural complexity, detection speed, and detection accuracy, this article proposes an improved YOLOv7-based electrowetting display defect detection model. The model effectively optimizes the detection performance of display defects, especially small target defects, by integrating GhostNetV2 modules, Acmix attention mechanisms, and NGWD (Normalized Gaussian Wasserstein Distance) Loss. At the same time, it reduces the parameter size of the network model and improves the inference efficiency of the network. This article evaluates the performance of an improved model using a self-constructed electrowetting display defect dataset. The experimental results show that the proposed improved model achieves an average detection rate (mAP) of 89.5% and an average inference time of 35.9 ms. Compared to the original network, the number of parameters and computational costs are reduced by 19.2% and 64.3%, respectively. Compared with current state-of-the-art detection network models, the proposed EW-YOLOv7 exhibits superior performance in detecting electrowetting display defects. This model helps to solve the problem of defect detection in industrial production of electrowetting display and assists the research team in quickly identifying the causes and locations of defects.</description><identifier>ISSN: 2227-9717</identifier><identifier>EISSN: 2227-9717</identifier><identifier>DOI: 10.3390/pr11072037</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Algorithms ; Complexity ; Computer applications ; Computing costs ; Contact angle ; Deep learning ; Defects ; Industrial production ; Inference ; Mathematical models ; Neural networks ; Parameters ; Performance evaluation ; Vision systems</subject><ispartof>Processes, 2023-07, Vol.11 (7), p.2037</ispartof><rights>COPYRIGHT 2023 MDPI AG</rights><rights>2023 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/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c334t-16b358b309111b207790f0a002c204d6c58e2378ffd0f3bbbe16b9c5008dae463</citedby><cites>FETCH-LOGICAL-c334t-16b358b309111b207790f0a002c204d6c58e2378ffd0f3bbbe16b9c5008dae463</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Zheng, Zihan</creatorcontrib><creatorcontrib>Chen, Ningxia</creatorcontrib><creatorcontrib>Wu, Jianhao</creatorcontrib><creatorcontrib>Xv, Zhixuan</creatorcontrib><creatorcontrib>Liu, Shuangyin</creatorcontrib><creatorcontrib>Luo, Zhijie</creatorcontrib><title>EW-YOLOv7: A Lightweight and Effective Detection Model for Small Defects in Electrowetting Display</title><title>Processes</title><description>In order to overcome the shortcomings of existing electrowetting display defect detection models in terms of computational complexity, structural complexity, detection speed, and detection accuracy, this article proposes an improved YOLOv7-based electrowetting display defect detection model. The model effectively optimizes the detection performance of display defects, especially small target defects, by integrating GhostNetV2 modules, Acmix attention mechanisms, and NGWD (Normalized Gaussian Wasserstein Distance) Loss. At the same time, it reduces the parameter size of the network model and improves the inference efficiency of the network. This article evaluates the performance of an improved model using a self-constructed electrowetting display defect dataset. The experimental results show that the proposed improved model achieves an average detection rate (mAP) of 89.5% and an average inference time of 35.9 ms. Compared to the original network, the number of parameters and computational costs are reduced by 19.2% and 64.3%, respectively. Compared with current state-of-the-art detection network models, the proposed EW-YOLOv7 exhibits superior performance in detecting electrowetting display defects. This model helps to solve the problem of defect detection in industrial production of electrowetting display and assists the research team in quickly identifying the causes and locations of defects.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Complexity</subject><subject>Computer applications</subject><subject>Computing costs</subject><subject>Contact angle</subject><subject>Deep learning</subject><subject>Defects</subject><subject>Industrial production</subject><subject>Inference</subject><subject>Mathematical models</subject><subject>Neural networks</subject><subject>Parameters</subject><subject>Performance evaluation</subject><subject>Vision systems</subject><issn>2227-9717</issn><issn>2227-9717</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpNUN9LwzAQDqLgmHvxLwj4JnRekrZpfRvb_AGVPaiITyVtk5nRNTXJNvbfmzJB7-Du4-777o5D6JrAlLEc7npLCHAKjJ-hEaWURzkn_PwfvkQT5zYQLCcsS9IRqpYf0eeqWO35PZ7hQq-__EEOEYuuwUulZO31XuKF9AMyHX4xjWyxMha_bkXbhs7AcVh3eNkGZM1Beq-7NV5o17fieIUulGidnPzmMXp_WL7Nn6Ji9fg8nxVRzVjsI5JWLMkqFk4jpKLAeQ4KBACtKcRNWieZpIxnSjWgWFVVMijyOgHIGiHjlI3RzWlub833TjpfbszOdmFlSbOYEUg4jQNremKtRStL3SnjraiDN3Kra9NJpUN9xpOc5JBmJAhuT4LaGuesVGVv9VbYY0mgHP5e_v2d_QCdUHLj</recordid><startdate>20230701</startdate><enddate>20230701</enddate><creator>Zheng, Zihan</creator><creator>Chen, Ningxia</creator><creator>Wu, Jianhao</creator><creator>Xv, Zhixuan</creator><creator>Liu, Shuangyin</creator><creator>Luo, Zhijie</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SR</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JG9</scope><scope>KB.</scope><scope>LK8</scope><scope>M7P</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope></search><sort><creationdate>20230701</creationdate><title>EW-YOLOv7: A Lightweight and Effective Detection Model for Small Defects in Electrowetting Display</title><author>Zheng, Zihan ; Chen, Ningxia ; Wu, Jianhao ; Xv, Zhixuan ; Liu, Shuangyin ; Luo, Zhijie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c334t-16b358b309111b207790f0a002c204d6c58e2378ffd0f3bbbe16b9c5008dae463</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Complexity</topic><topic>Computer applications</topic><topic>Computing costs</topic><topic>Contact angle</topic><topic>Deep learning</topic><topic>Defects</topic><topic>Industrial production</topic><topic>Inference</topic><topic>Mathematical models</topic><topic>Neural networks</topic><topic>Parameters</topic><topic>Performance evaluation</topic><topic>Vision systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Zihan</creatorcontrib><creatorcontrib>Chen, Ningxia</creatorcontrib><creatorcontrib>Wu, Jianhao</creatorcontrib><creatorcontrib>Xv, Zhixuan</creatorcontrib><creatorcontrib>Liu, Shuangyin</creatorcontrib><creatorcontrib>Luo, Zhijie</creatorcontrib><collection>CrossRef</collection><collection>Engineered Materials Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Materials Research Database</collection><collection>Materials Science Database</collection><collection>ProQuest Biological Science Collection</collection><collection>Biological Science Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><jtitle>Processes</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zheng, Zihan</au><au>Chen, Ningxia</au><au>Wu, Jianhao</au><au>Xv, Zhixuan</au><au>Liu, Shuangyin</au><au>Luo, Zhijie</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EW-YOLOv7: A Lightweight and Effective Detection Model for Small Defects in Electrowetting Display</atitle><jtitle>Processes</jtitle><date>2023-07-01</date><risdate>2023</risdate><volume>11</volume><issue>7</issue><spage>2037</spage><pages>2037-</pages><issn>2227-9717</issn><eissn>2227-9717</eissn><abstract>In order to overcome the shortcomings of existing electrowetting display defect detection models in terms of computational complexity, structural complexity, detection speed, and detection accuracy, this article proposes an improved YOLOv7-based electrowetting display defect detection model. The model effectively optimizes the detection performance of display defects, especially small target defects, by integrating GhostNetV2 modules, Acmix attention mechanisms, and NGWD (Normalized Gaussian Wasserstein Distance) Loss. At the same time, it reduces the parameter size of the network model and improves the inference efficiency of the network. This article evaluates the performance of an improved model using a self-constructed electrowetting display defect dataset. The experimental results show that the proposed improved model achieves an average detection rate (mAP) of 89.5% and an average inference time of 35.9 ms. Compared to the original network, the number of parameters and computational costs are reduced by 19.2% and 64.3%, respectively. Compared with current state-of-the-art detection network models, the proposed EW-YOLOv7 exhibits superior performance in detecting electrowetting display defects. This model helps to solve the problem of defect detection in industrial production of electrowetting display and assists the research team in quickly identifying the causes and locations of defects.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/pr11072037</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2227-9717
ispartof Processes, 2023-07, Vol.11 (7), p.2037
issn 2227-9717
2227-9717
language eng
recordid cdi_proquest_journals_2843105724
source MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals
subjects Accuracy
Algorithms
Complexity
Computer applications
Computing costs
Contact angle
Deep learning
Defects
Industrial production
Inference
Mathematical models
Neural networks
Parameters
Performance evaluation
Vision systems
title EW-YOLOv7: A Lightweight and Effective Detection Model for Small Defects in Electrowetting Display
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T18%3A12%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=EW-YOLOv7:%20A%20Lightweight%20and%20Effective%20Detection%20Model%20for%20Small%20Defects%20in%20Electrowetting%20Display&rft.jtitle=Processes&rft.au=Zheng,%20Zihan&rft.date=2023-07-01&rft.volume=11&rft.issue=7&rft.spage=2037&rft.pages=2037-&rft.issn=2227-9717&rft.eissn=2227-9717&rft_id=info:doi/10.3390/pr11072037&rft_dat=%3Cgale_proqu%3EA759190681%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2843105724&rft_id=info:pmid/&rft_galeid=A759190681&rfr_iscdi=true