Robust feature extraction method based on run-length compensation for degraded character recognition

Robust feature extraction method based on run-length compensation for degraded character recognition

Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approxi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Systems and computers in Japan 2004-08, Vol.35 (9), p.1-9
Hauptverfasser: Mori, Minoru, Sawaki, Minako, Hagita, Norihiro, Murase, Hiroshi, Mukawa, Naoki
Format: Artikel
Sprache:eng
Schlagworte:
degradation estimation
direction contributivity
feature extraction
OCR
run-length compensation
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 9
container_issue 9
container_start_page 1
container_title Systems and computers in Japan
container_volume 35
creator Mori, Minoru
Sawaki, Minako
Hagita, Norihiro
Murase, Hiroshi
Mukawa, Naoki
description Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approximately extracting directional run‐lengths of strokes from degraded handwritten characters. This technique is applied to the conventional feature vector based on directional run‐lengths. Experiments for handwritten characters with additive or subtractive noise show that the proposed feature is superior to conventional ones over a wide range of the degree of noise. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(9): 1–9, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10643
doi_str_mv 10.1002/scj.10643
format Article
fullrecord <record><control><sourceid>istex_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1002_scj_10643</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>ark_67375_WNG_KG83TRMS_9</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1803-ad380a9ffcaa7fe1e72cba976a7c2041b016212a5fe3194e10447ad1c286ce2c3</originalsourceid><addsrcrecordid>eNp1kE1PwkAQhjdGExE9-A_26qGyH2XbHg1R_EBNAKO3zXQ7C0Voye42wr-3gHozc5h5k-eZw0vIJWfXnDHR82bRHiqWR6TD-4JFKo0_jkmHpamIuFLqlJx5v2CMt5N1SDGu88YHahFC45DiJjgwoawrusIwrwuag8eCttk1VbTEahbm1NSrNVYe9pytHS1w5qBoOTOHnY-OOjT1rCp3yDk5sbD0ePGzu-Tt7nY6uI9Gr8OHwc0oMjxlMoJCpgwyaw1AYpFjIkwOWaIgMYLFPGdcCS6gb1HyLEbO4jiBghuRKoPCyC65Ovw1rvbeodVrV67AbTVnelePbuvR-3patndgv8olbv8H9WTw-GtEB6P0ATd_BrhPrRKZ9PX7y1A_DVM5HT9PdCa_Aa7peJE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Robust feature extraction method based on run-length compensation for degraded character recognition</title><source>Wiley Online Library Journals Frontfile Complete</source><creator>Mori, Minoru ; Sawaki, Minako ; Hagita, Norihiro ; Murase, Hiroshi ; Mukawa, Naoki</creator><creatorcontrib>Mori, Minoru ; Sawaki, Minako ; Hagita, Norihiro ; Murase, Hiroshi ; Mukawa, Naoki</creatorcontrib><description>Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approximately extracting directional run‐lengths of strokes from degraded handwritten characters. This technique is applied to the conventional feature vector based on directional run‐lengths. Experiments for handwritten characters with additive or subtractive noise show that the proposed feature is superior to conventional ones over a wide range of the degree of noise. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(9): 1–9, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10643</description><identifier>ISSN: 0882-1666</identifier><identifier>EISSN: 1520-684X</identifier><identifier>DOI: 10.1002/scj.10643</identifier><language>eng</language><publisher>Hoboken: Wiley Subscription Services, Inc., A Wiley Company</publisher><subject>degradation estimation ; direction contributivity ; feature extraction ; OCR ; run-length compensation</subject><ispartof>Systems and computers in Japan, 2004-08, Vol.35 (9), p.1-9</ispartof><rights>Copyright © 2004 Wiley Periodicals, Inc.</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1803-ad380a9ffcaa7fe1e72cba976a7c2041b016212a5fe3194e10447ad1c286ce2c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fscj.10643$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fscj.10643$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,776,780,1411,27901,27902,45550,45551</link.rule.ids></links><search><creatorcontrib>Mori, Minoru</creatorcontrib><creatorcontrib>Sawaki, Minako</creatorcontrib><creatorcontrib>Hagita, Norihiro</creatorcontrib><creatorcontrib>Murase, Hiroshi</creatorcontrib><creatorcontrib>Mukawa, Naoki</creatorcontrib><title>Robust feature extraction method based on run-length compensation for degraded character recognition</title><title>Systems and computers in Japan</title><addtitle>Syst. Comp. Jpn</addtitle><description>Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approximately extracting directional run‐lengths of strokes from degraded handwritten characters. This technique is applied to the conventional feature vector based on directional run‐lengths. Experiments for handwritten characters with additive or subtractive noise show that the proposed feature is superior to conventional ones over a wide range of the degree of noise. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(9): 1–9, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10643</description><subject>degradation estimation</subject><subject>direction contributivity</subject><subject>feature extraction</subject><subject>OCR</subject><subject>run-length compensation</subject><issn>0882-1666</issn><issn>1520-684X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2004</creationdate><recordtype>article</recordtype><recordid>eNp1kE1PwkAQhjdGExE9-A_26qGyH2XbHg1R_EBNAKO3zXQ7C0Voye42wr-3gHozc5h5k-eZw0vIJWfXnDHR82bRHiqWR6TD-4JFKo0_jkmHpamIuFLqlJx5v2CMt5N1SDGu88YHahFC45DiJjgwoawrusIwrwuag8eCttk1VbTEahbm1NSrNVYe9pytHS1w5qBoOTOHnY-OOjT1rCp3yDk5sbD0ePGzu-Tt7nY6uI9Gr8OHwc0oMjxlMoJCpgwyaw1AYpFjIkwOWaIgMYLFPGdcCS6gb1HyLEbO4jiBghuRKoPCyC65Ovw1rvbeodVrV67AbTVnelePbuvR-3patndgv8olbv8H9WTw-GtEB6P0ATd_BrhPrRKZ9PX7y1A_DVM5HT9PdCa_Aa7peJE</recordid><startdate>200408</startdate><enddate>200408</enddate><creator>Mori, Minoru</creator><creator>Sawaki, Minako</creator><creator>Hagita, Norihiro</creator><creator>Murase, Hiroshi</creator><creator>Mukawa, Naoki</creator><general>Wiley Subscription Services, Inc., A Wiley Company</general><scope>BSCLL</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>200408</creationdate><title>Robust feature extraction method based on run-length compensation for degraded character recognition</title><author>Mori, Minoru ; Sawaki, Minako ; Hagita, Norihiro ; Murase, Hiroshi ; Mukawa, Naoki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1803-ad380a9ffcaa7fe1e72cba976a7c2041b016212a5fe3194e10447ad1c286ce2c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2004</creationdate><topic>degradation estimation</topic><topic>direction contributivity</topic><topic>feature extraction</topic><topic>OCR</topic><topic>run-length compensation</topic><toplevel>online_resources</toplevel><creatorcontrib>Mori, Minoru</creatorcontrib><creatorcontrib>Sawaki, Minako</creatorcontrib><creatorcontrib>Hagita, Norihiro</creatorcontrib><creatorcontrib>Murase, Hiroshi</creatorcontrib><creatorcontrib>Mukawa, Naoki</creatorcontrib><collection>Istex</collection><collection>CrossRef</collection><jtitle>Systems and computers in Japan</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mori, Minoru</au><au>Sawaki, Minako</au><au>Hagita, Norihiro</au><au>Murase, Hiroshi</au><au>Mukawa, Naoki</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robust feature extraction method based on run-length compensation for degraded character recognition</atitle><jtitle>Systems and computers in Japan</jtitle><addtitle>Syst. Comp. Jpn</addtitle><date>2004-08</date><risdate>2004</risdate><volume>35</volume><issue>9</issue><spage>1</spage><epage>9</epage><pages>1-9</pages><issn>0882-1666</issn><eissn>1520-684X</eissn><abstract>Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approximately extracting directional run‐lengths of strokes from degraded handwritten characters. This technique is applied to the conventional feature vector based on directional run‐lengths. Experiments for handwritten characters with additive or subtractive noise show that the proposed feature is superior to conventional ones over a wide range of the degree of noise. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(9): 1–9, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10643</abstract><cop>Hoboken</cop><pub>Wiley Subscription Services, Inc., A Wiley Company</pub><doi>10.1002/scj.10643</doi><tpages>9</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0882-1666
ispartof Systems and computers in Japan, 2004-08, Vol.35 (9), p.1-9
issn 0882-1666
1520-684X
language eng
recordid cdi_crossref_primary_10_1002_scj_10643
source Wiley Online Library Journals Frontfile Complete
subjects degradation estimation
direction contributivity
feature extraction
OCR
run-length compensation
title Robust feature extraction method based on run-length compensation for degraded character recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T13%3A44%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-istex_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Robust%20feature%20extraction%20method%20based%20on%20run-length%20compensation%20for%20degraded%20character%20recognition&rft.jtitle=Systems%20and%20computers%20in%20Japan&rft.au=Mori,%20Minoru&rft.date=2004-08&rft.volume=35&rft.issue=9&rft.spage=1&rft.epage=9&rft.pages=1-9&rft.issn=0882-1666&rft.eissn=1520-684X&rft_id=info:doi/10.1002/scj.10643&rft_dat=%3Cistex_cross%3Eark_67375_WNG_KG83TRMS_9%3C/istex_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true