Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning

As key steps of lithography, the development of resist materials and the exploration of new materials are important to meet market demands from the semiconductor industry. During the development, resist materials are usually evaluated by the information extracted from their scanning electron microsc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Japanese Journal of Applied Physics 2022-05, Vol.61 (5), p.56505
Hauptverfasser: Jin, Yuqing, Kozawa, Takahiro
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 5
container_start_page 56505
container_title Japanese Journal of Applied Physics
container_volume 61
creator Jin, Yuqing
Kozawa, Takahiro
description As key steps of lithography, the development of resist materials and the exploration of new materials are important to meet market demands from the semiconductor industry. During the development, resist materials are usually evaluated by the information extracted from their scanning electron microscopy (SEM) images. The information extracted from SEM images is not always accurate owing to technical limitation. Accurate information extraction is also useful for the prediction of an etched substrate pattern. In this paper, we reported a strategy to classify the image pixels of line-and-space resist patterns into line, space, and edge classes, using unsupervised machine learning. Brightness and coordination information was integrated into the classification method. The high reliability in classification was demonstrated by hierarchical clustering based on its information integrating ability. Among all the methods of hierarchical clustering examined, the centroid method was the most accurate strategy for extracting information from a single SEM image.
doi_str_mv 10.35848/1347-4065/ac56b5
format Article
fullrecord <record><control><sourceid>proquest_iop_j</sourceid><recordid>TN_cdi_proquest_journals_2664072616</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2664072616</sourcerecordid><originalsourceid>FETCH-LOGICAL-c410t-4c4dc6ee0f69ce3c1bb18be43c78ac3f56bc08f43506e906437c93bed55d94d73</originalsourceid><addsrcrecordid>eNp1kM1u1TAQhS0EEpfCA7CzxIYFae34J8myumoBqRIbWFvOZFJ8leu4nqRS36CPjdOLyoauRvZ854zOYeyjFOfKtLq9kEo3lRbWXHgwtjev2O756zXbCVHLSnd1_Za9IzqUpzVa7tjjfvJEYQzglzBHPo98ChHpC6fkYZs-DhyHW6Rtl5ECLTz5ZcEciYfICXyMId5ynBCWXDyOAfJMMKcHHo5-U660AWukNWG-D4QDP3r4XQ7xCX3e5O_Zm9FPhB_-zjP26_rq5_5bdfPj6_f95U0FWoql0qAHsIhitB2gAtn3su1RK2haD2os0UG0o1ZGWOyE1aqBTvU4GDN0emjUGft08k15vluRFneY1xzLSVdbq0VTW2kLJU_UloQyji7lkiU_OCncU-Fua9dt7bpT4UXz-aQJc_pnejj45Kx0xgljjTAuDWNBq_-gL1v_AYRDktY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2664072616</pqid></control><display><type>article</type><title>Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning</title><source>Institute of Physics Journals</source><creator>Jin, Yuqing ; Kozawa, Takahiro</creator><creatorcontrib>Jin, Yuqing ; Kozawa, Takahiro</creatorcontrib><description>As key steps of lithography, the development of resist materials and the exploration of new materials are important to meet market demands from the semiconductor industry. During the development, resist materials are usually evaluated by the information extracted from their scanning electron microscopy (SEM) images. The information extracted from SEM images is not always accurate owing to technical limitation. Accurate information extraction is also useful for the prediction of an etched substrate pattern. In this paper, we reported a strategy to classify the image pixels of line-and-space resist patterns into line, space, and edge classes, using unsupervised machine learning. Brightness and coordination information was integrated into the classification method. The high reliability in classification was demonstrated by hierarchical clustering based on its information integrating ability. Among all the methods of hierarchical clustering examined, the centroid method was the most accurate strategy for extracting information from a single SEM image.</description><identifier>ISSN: 0021-4922</identifier><identifier>EISSN: 1347-4065</identifier><identifier>DOI: 10.35848/1347-4065/ac56b5</identifier><identifier>CODEN: JJAPB6</identifier><language>eng</language><publisher>Tokyo: IOP Publishing</publisher><subject>Centroids ; Cluster analysis ; Clustering ; EB lithography ; EUV lithography ; Image classification ; Industrial development ; Information retrieval ; Machine learning ; resist image ; Scanning electron microscopy ; SEM images ; Substrates ; Unsupervised learning ; unsupervised machine learning</subject><ispartof>Japanese Journal of Applied Physics, 2022-05, Vol.61 (5), p.56505</ispartof><rights>2022 The Japan Society of Applied Physics</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c410t-4c4dc6ee0f69ce3c1bb18be43c78ac3f56bc08f43506e906437c93bed55d94d73</citedby><cites>FETCH-LOGICAL-c410t-4c4dc6ee0f69ce3c1bb18be43c78ac3f56bc08f43506e906437c93bed55d94d73</cites><orcidid>0000-0002-1692-2830 ; 0000-0002-0124-5240</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://iopscience.iop.org/article/10.35848/1347-4065/ac56b5/pdf$$EPDF$$P50$$Giop$$H</linktopdf><link.rule.ids>314,780,784,27924,27925,53846,53893</link.rule.ids></links><search><creatorcontrib>Jin, Yuqing</creatorcontrib><creatorcontrib>Kozawa, Takahiro</creatorcontrib><title>Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning</title><title>Japanese Journal of Applied Physics</title><addtitle>Jpn. J. Appl. Phys</addtitle><description>As key steps of lithography, the development of resist materials and the exploration of new materials are important to meet market demands from the semiconductor industry. During the development, resist materials are usually evaluated by the information extracted from their scanning electron microscopy (SEM) images. The information extracted from SEM images is not always accurate owing to technical limitation. Accurate information extraction is also useful for the prediction of an etched substrate pattern. In this paper, we reported a strategy to classify the image pixels of line-and-space resist patterns into line, space, and edge classes, using unsupervised machine learning. Brightness and coordination information was integrated into the classification method. The high reliability in classification was demonstrated by hierarchical clustering based on its information integrating ability. Among all the methods of hierarchical clustering examined, the centroid method was the most accurate strategy for extracting information from a single SEM image.</description><subject>Centroids</subject><subject>Cluster analysis</subject><subject>Clustering</subject><subject>EB lithography</subject><subject>EUV lithography</subject><subject>Image classification</subject><subject>Industrial development</subject><subject>Information retrieval</subject><subject>Machine learning</subject><subject>resist image</subject><subject>Scanning electron microscopy</subject><subject>SEM images</subject><subject>Substrates</subject><subject>Unsupervised learning</subject><subject>unsupervised machine learning</subject><issn>0021-4922</issn><issn>1347-4065</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp1kM1u1TAQhS0EEpfCA7CzxIYFae34J8myumoBqRIbWFvOZFJ8leu4nqRS36CPjdOLyoauRvZ854zOYeyjFOfKtLq9kEo3lRbWXHgwtjev2O756zXbCVHLSnd1_Za9IzqUpzVa7tjjfvJEYQzglzBHPo98ChHpC6fkYZs-DhyHW6Rtl5ECLTz5ZcEciYfICXyMId5ynBCWXDyOAfJMMKcHHo5-U660AWukNWG-D4QDP3r4XQ7xCX3e5O_Zm9FPhB_-zjP26_rq5_5bdfPj6_f95U0FWoql0qAHsIhitB2gAtn3su1RK2haD2os0UG0o1ZGWOyE1aqBTvU4GDN0emjUGft08k15vluRFneY1xzLSVdbq0VTW2kLJU_UloQyji7lkiU_OCncU-Fua9dt7bpT4UXz-aQJc_pnejj45Kx0xgljjTAuDWNBq_-gL1v_AYRDktY</recordid><startdate>20220501</startdate><enddate>20220501</enddate><creator>Jin, Yuqing</creator><creator>Kozawa, Takahiro</creator><general>IOP Publishing</general><general>Japanese Journal of Applied Physics</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-1692-2830</orcidid><orcidid>https://orcid.org/0000-0002-0124-5240</orcidid></search><sort><creationdate>20220501</creationdate><title>Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning</title><author>Jin, Yuqing ; Kozawa, Takahiro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c410t-4c4dc6ee0f69ce3c1bb18be43c78ac3f56bc08f43506e906437c93bed55d94d73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Centroids</topic><topic>Cluster analysis</topic><topic>Clustering</topic><topic>EB lithography</topic><topic>EUV lithography</topic><topic>Image classification</topic><topic>Industrial development</topic><topic>Information retrieval</topic><topic>Machine learning</topic><topic>resist image</topic><topic>Scanning electron microscopy</topic><topic>SEM images</topic><topic>Substrates</topic><topic>Unsupervised learning</topic><topic>unsupervised machine learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jin, Yuqing</creatorcontrib><creatorcontrib>Kozawa, Takahiro</creatorcontrib><collection>CrossRef</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Japanese Journal of Applied Physics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jin, Yuqing</au><au>Kozawa, Takahiro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning</atitle><jtitle>Japanese Journal of Applied Physics</jtitle><addtitle>Jpn. J. Appl. Phys</addtitle><date>2022-05-01</date><risdate>2022</risdate><volume>61</volume><issue>5</issue><spage>56505</spage><pages>56505-</pages><issn>0021-4922</issn><eissn>1347-4065</eissn><coden>JJAPB6</coden><abstract>As key steps of lithography, the development of resist materials and the exploration of new materials are important to meet market demands from the semiconductor industry. During the development, resist materials are usually evaluated by the information extracted from their scanning electron microscopy (SEM) images. The information extracted from SEM images is not always accurate owing to technical limitation. Accurate information extraction is also useful for the prediction of an etched substrate pattern. In this paper, we reported a strategy to classify the image pixels of line-and-space resist patterns into line, space, and edge classes, using unsupervised machine learning. Brightness and coordination information was integrated into the classification method. The high reliability in classification was demonstrated by hierarchical clustering based on its information integrating ability. Among all the methods of hierarchical clustering examined, the centroid method was the most accurate strategy for extracting information from a single SEM image.</abstract><cop>Tokyo</cop><pub>IOP Publishing</pub><doi>10.35848/1347-4065/ac56b5</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-1692-2830</orcidid><orcidid>https://orcid.org/0000-0002-0124-5240</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0021-4922
ispartof Japanese Journal of Applied Physics, 2022-05, Vol.61 (5), p.56505
issn 0021-4922
1347-4065
language eng
recordid cdi_proquest_journals_2664072616
source Institute of Physics Journals
subjects Centroids
Cluster analysis
Clustering
EB lithography
EUV lithography
Image classification
Industrial development
Information retrieval
Machine learning
resist image
Scanning electron microscopy
SEM images
Substrates
Unsupervised learning
unsupervised machine learning
title Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A25%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_iop_j&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Classification%20of%20lines,%20spaces,%20and%20edges%20of%20resist%20patterns%20in%20scanning%20electron%20microscopy%20images%20using%20unsupervised%20machine%20learning&rft.jtitle=Japanese%20Journal%20of%20Applied%20Physics&rft.au=Jin,%20Yuqing&rft.date=2022-05-01&rft.volume=61&rft.issue=5&rft.spage=56505&rft.pages=56505-&rft.issn=0021-4922&rft.eissn=1347-4065&rft.coden=JJAPB6&rft_id=info:doi/10.35848/1347-4065/ac56b5&rft_dat=%3Cproquest_iop_j%3E2664072616%3C/proquest_iop_j%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2664072616&rft_id=info:pmid/&rfr_iscdi=true