Loading…
Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network
Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneousl...
Saved in:
| Published in: | Crystals (Basel) 2021-09, Vol.11 (9), p.1048 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213 |
| container_end_page | |
| container_issue | 9 |
| container_start_page | 1048 |
| container_title | Crystals (Basel) |
| container_volume | 11 |
| creator | Huang, Che-Hsuan Lee, Pei-Hsuan Chang, Shu-Hsiu Kuo, Hao-Chung Sun, Chia-Wei Lin, Chien-Chung Tsai, Chun-Lin Liu, Xinke |
| description | Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneously generate anomaly alerts and reduce labeling costs. This AOI system works by deploying the GANomaly neural network and the supervised network to the manufacturing system. To improve the ability to distinguish anomaly items from normal items in industry and enhance the overall performance of the manufacturing process, the system uses the structural similarity index (SSIM) as part of the loss function as well as the scoring parameters. Thus, the proposed system will achieve the requirements of smart factories in the future (Industry 4.0). |
| doi_str_mv | 10.3390/cryst11091048 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_17d705d6930e4a8887e8eb37a1a97b00</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_17d705d6930e4a8887e8eb37a1a97b00</doaj_id><sourcerecordid>2576386835</sourcerecordid><originalsourceid>FETCH-LOGICAL-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213</originalsourceid><addsrcrecordid>eNpVUcFu2zAMNYoNaNH1uLuBnb1JoS3Kx6Dt2gDpelnOAmPRqbLE8iQ5RX-g3121KYaOl0eQj-8RZFF8leI7QCt-dOEpJilFK0WtT4qzmUCoamhmnz7kp8VFjFuRA5VAlGfF83xKfk-JbXk_JtfRrlwMceQuOT-Ud5wevC17H8ql2zyk6nrvUnLDprxy3nJ5xX1mZkjvA6v42lwNcRo5HFzMsjc8cKDkDlzO7YFDpOCyyy-ewhukRx_-fCk-97SLfPGO58Xq5_Xvy9tqeX-zuJwvqw5QpArXLYlOSknUkmS2GpRCrLkXQkIrgRgtQd_UXb_WKBW1gLbvrABUaibhvFgcda2nrRmD21N4Mp6ceSv4sDEU8hl2bCRaFI1VLQiuSWuNrHkNSJJaXAuRtb4dtcbg_04ck9n6KQx5fTNrUIFWGprMqo6sLvgYA_f_XKUwr58z_30OXgDbBo25</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2576386835</pqid></control><display><type>article</type><title>Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Huang, Che-Hsuan ; Lee, Pei-Hsuan ; Chang, Shu-Hsiu ; Kuo, Hao-Chung ; Sun, Chia-Wei ; Lin, Chien-Chung ; Tsai, Chun-Lin ; Liu, Xinke</creator><creatorcontrib>Huang, Che-Hsuan ; Lee, Pei-Hsuan ; Chang, Shu-Hsiu ; Kuo, Hao-Chung ; Sun, Chia-Wei ; Lin, Chien-Chung ; Tsai, Chun-Lin ; Liu, Xinke</creatorcontrib><description>Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneously generate anomaly alerts and reduce labeling costs. This AOI system works by deploying the GANomaly neural network and the supervised network to the manufacturing system. To improve the ability to distinguish anomaly items from normal items in industry and enhance the overall performance of the manufacturing process, the system uses the structural similarity index (SSIM) as part of the loss function as well as the scoring parameters. Thus, the proposed system will achieve the requirements of smart factories in the future (Industry 4.0).</description><identifier>ISSN: 2073-4352</identifier><identifier>EISSN: 2073-4352</identifier><identifier>DOI: 10.3390/cryst11091048</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>abnormal detection ; Algorithms ; Datasets ; Defects ; Factories ; GAN ; Inspection ; LED ; Light emitting diodes ; Machine learning ; Manufacturing ; Neural networks ; Object recognition ; unsupervised learning</subject><ispartof>Crystals (Basel), 2021-09, Vol.11 (9), p.1048</ispartof><rights>2021 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-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213</citedby><cites>FETCH-LOGICAL-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213</cites><orcidid>0000-0001-8656-1922 ; 0000-0001-6767-6046 ; 0000-0002-9373-4649</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2576386835/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2576386835?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,25753,27924,27925,37012,44590,75126</link.rule.ids></links><search><creatorcontrib>Huang, Che-Hsuan</creatorcontrib><creatorcontrib>Lee, Pei-Hsuan</creatorcontrib><creatorcontrib>Chang, Shu-Hsiu</creatorcontrib><creatorcontrib>Kuo, Hao-Chung</creatorcontrib><creatorcontrib>Sun, Chia-Wei</creatorcontrib><creatorcontrib>Lin, Chien-Chung</creatorcontrib><creatorcontrib>Tsai, Chun-Lin</creatorcontrib><creatorcontrib>Liu, Xinke</creatorcontrib><title>Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network</title><title>Crystals (Basel)</title><description>Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneously generate anomaly alerts and reduce labeling costs. This AOI system works by deploying the GANomaly neural network and the supervised network to the manufacturing system. To improve the ability to distinguish anomaly items from normal items in industry and enhance the overall performance of the manufacturing process, the system uses the structural similarity index (SSIM) as part of the loss function as well as the scoring parameters. Thus, the proposed system will achieve the requirements of smart factories in the future (Industry 4.0).</description><subject>abnormal detection</subject><subject>Algorithms</subject><subject>Datasets</subject><subject>Defects</subject><subject>Factories</subject><subject>GAN</subject><subject>Inspection</subject><subject>LED</subject><subject>Light emitting diodes</subject><subject>Machine learning</subject><subject>Manufacturing</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>unsupervised learning</subject><issn>2073-4352</issn><issn>2073-4352</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpVUcFu2zAMNYoNaNH1uLuBnb1JoS3Kx6Dt2gDpelnOAmPRqbLE8iQ5RX-g3121KYaOl0eQj-8RZFF8leI7QCt-dOEpJilFK0WtT4qzmUCoamhmnz7kp8VFjFuRA5VAlGfF83xKfk-JbXk_JtfRrlwMceQuOT-Ud5wevC17H8ql2zyk6nrvUnLDprxy3nJ5xX1mZkjvA6v42lwNcRo5HFzMsjc8cKDkDlzO7YFDpOCyyy-ewhukRx_-fCk-97SLfPGO58Xq5_Xvy9tqeX-zuJwvqw5QpArXLYlOSknUkmS2GpRCrLkXQkIrgRgtQd_UXb_WKBW1gLbvrABUaibhvFgcda2nrRmD21N4Mp6ceSv4sDEU8hl2bCRaFI1VLQiuSWuNrHkNSJJaXAuRtb4dtcbg_04ck9n6KQx5fTNrUIFWGprMqo6sLvgYA_f_XKUwr58z_30OXgDbBo25</recordid><startdate>20210901</startdate><enddate>20210901</enddate><creator>Huang, Che-Hsuan</creator><creator>Lee, Pei-Hsuan</creator><creator>Chang, Shu-Hsiu</creator><creator>Kuo, Hao-Chung</creator><creator>Sun, Chia-Wei</creator><creator>Lin, Chien-Chung</creator><creator>Tsai, Chun-Lin</creator><creator>Liu, Xinke</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>JG9</scope><scope>KB.</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-8656-1922</orcidid><orcidid>https://orcid.org/0000-0001-6767-6046</orcidid><orcidid>https://orcid.org/0000-0002-9373-4649</orcidid></search><sort><creationdate>20210901</creationdate><title>Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network</title><author>Huang, Che-Hsuan ; Lee, Pei-Hsuan ; Chang, Shu-Hsiu ; Kuo, Hao-Chung ; Sun, Chia-Wei ; Lin, Chien-Chung ; Tsai, Chun-Lin ; Liu, Xinke</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>abnormal detection</topic><topic>Algorithms</topic><topic>Datasets</topic><topic>Defects</topic><topic>Factories</topic><topic>GAN</topic><topic>Inspection</topic><topic>LED</topic><topic>Light emitting diodes</topic><topic>Machine learning</topic><topic>Manufacturing</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>unsupervised learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Huang, Che-Hsuan</creatorcontrib><creatorcontrib>Lee, Pei-Hsuan</creatorcontrib><creatorcontrib>Chang, Shu-Hsiu</creatorcontrib><creatorcontrib>Kuo, Hao-Chung</creatorcontrib><creatorcontrib>Sun, Chia-Wei</creatorcontrib><creatorcontrib>Lin, Chien-Chung</creatorcontrib><creatorcontrib>Tsai, Chun-Lin</creatorcontrib><creatorcontrib>Liu, Xinke</creatorcontrib><collection>CrossRef</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>Materials Research Database</collection><collection>Materials Science Database</collection><collection>Materials science collection</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Directory of Open Access Journals</collection><jtitle>Crystals (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Huang, Che-Hsuan</au><au>Lee, Pei-Hsuan</au><au>Chang, Shu-Hsiu</au><au>Kuo, Hao-Chung</au><au>Sun, Chia-Wei</au><au>Lin, Chien-Chung</au><au>Tsai, Chun-Lin</au><au>Liu, Xinke</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network</atitle><jtitle>Crystals (Basel)</jtitle><date>2021-09-01</date><risdate>2021</risdate><volume>11</volume><issue>9</issue><spage>1048</spage><pages>1048-</pages><issn>2073-4352</issn><eissn>2073-4352</eissn><abstract>Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneously generate anomaly alerts and reduce labeling costs. This AOI system works by deploying the GANomaly neural network and the supervised network to the manufacturing system. To improve the ability to distinguish anomaly items from normal items in industry and enhance the overall performance of the manufacturing process, the system uses the structural similarity index (SSIM) as part of the loss function as well as the scoring parameters. Thus, the proposed system will achieve the requirements of smart factories in the future (Industry 4.0).</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/cryst11091048</doi><orcidid>https://orcid.org/0000-0001-8656-1922</orcidid><orcidid>https://orcid.org/0000-0001-6767-6046</orcidid><orcidid>https://orcid.org/0000-0002-9373-4649</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2073-4352 |
| ispartof | Crystals (Basel), 2021-09, Vol.11 (9), p.1048 |
| issn | 2073-4352 2073-4352 |
| language | eng |
| recordid | cdi_doaj_primary_oai_doaj_org_article_17d705d6930e4a8887e8eb37a1a97b00 |
| source | Publicly Available Content Database (Proquest) (PQ_SDU_P3) |
| subjects | abnormal detection Algorithms Datasets Defects Factories GAN Inspection LED Light emitting diodes Machine learning Manufacturing Neural networks Object recognition unsupervised learning |
| title | Automated Optical Inspection Method for Light-Emitting Diode Defect Detection Using Unsupervised Generative Adversarial Neural Network |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T19%3A11%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20Optical%20Inspection%20Method%20for%20Light-Emitting%20Diode%20Defect%20Detection%20Using%20Unsupervised%20Generative%20Adversarial%20Neural%20Network&rft.jtitle=Crystals%20(Basel)&rft.au=Huang,%20Che-Hsuan&rft.date=2021-09-01&rft.volume=11&rft.issue=9&rft.spage=1048&rft.pages=1048-&rft.issn=2073-4352&rft.eissn=2073-4352&rft_id=info:doi/10.3390/cryst11091048&rft_dat=%3Cproquest_doaj_%3E2576386835%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c370t-7b9a0c111aa9a1eed8366774ef0013913ae7da3f54cfb8716a937dfcd03766213%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2576386835&rft_id=info:pmid/&rfr_iscdi=true |