WO2008111399A1 - 単語認識方法および単語認識プログラム - Google Patents

単語認識方法および単語認識プログラム Download PDF

Info

Publication number
WO2008111399A1
WO2008111399A1 PCT/JP2008/053433 JP2008053433W WO2008111399A1 WO 2008111399 A1 WO2008111399 A1 WO 2008111399A1 JP 2008053433 W JP2008053433 W JP 2008053433W WO 2008111399 A1 WO2008111399 A1 WO 2008111399A1
Authority
WO
WIPO (PCT)
Prior art keywords
character
word
word recognizing
quality score
candidate
Prior art date
Application number
PCT/JP2008/053433
Other languages
English (en)
French (fr)
Inventor
Tomoyuki Hamamura
Original Assignee
Kabushiki Kaisha Toshiba
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Kabushiki Kaisha Toshiba filed Critical Kabushiki Kaisha Toshiba
Priority to EP08712055.6A priority Critical patent/EP2138959B1/en
Priority to US12/184,456 priority patent/US8208685B2/en
Publication of WO2008111399A1 publication Critical patent/WO2008111399A1/ja

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/768—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using context analysis, e.g. recognition aided by known co-occurring patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/26—Techniques for post-processing, e.g. correcting the recognition result
    • G06V30/262—Techniques for post-processing, e.g. correcting the recognition result using context analysis, e.g. lexical, syntactic or semantic context
    • G06V30/268—Lexical context
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition

Abstract

　被読取物上に記載された文字情報の文字読取を行って得られる各単語候補に対する認識処理を行う単語認識方法が提供される。この単語認識方法は、上記各単語候補に対し、単語辞書内の複数の単語との照合を行い、双方が一致する度合いを示すマッチングスコアを単語毎に算出するマッチング処理ステップ（１２）と、上記各単語候補を構成する文字候補が任意の文字に一致する度合いを示す文字品質スコアを算出する文字品質スコア算出ステップ（１３）と、上記文字品質スコア算出ステップ（１３）で得られる文字品質スコアを元に上記マッチング処理ステップ（１２）で得られるマッチングスコアを補正する補正ステップ（１４）とを有する。
PCT/JP2008/053433 2007-03-14 2008-02-27 単語認識方法および単語認識プログラム WO2008111399A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP08712055.6A EP2138959B1 (en) 2007-03-14 2008-02-27 Word recognizing method and word recognizing program
US12/184,456 US8208685B2 (en) 2007-03-14 2008-08-01 Word recognition method and word recognition program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2007065522A JP4672692B2 (ja) 2007-03-14 2007-03-14 単語認識システムおよび単語認識プログラム
JP2007-065522 2007-03-14

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US12/184,456 Continuation US8208685B2 (en) 2007-03-14 2008-08-01 Word recognition method and word recognition program

Publications (1)

Publication Number Publication Date
WO2008111399A1 true WO2008111399A1 (ja) 2008-09-18

Family

ID=39759341

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2008/053433 WO2008111399A1 (ja) 2007-03-14 2008-02-27 単語認識方法および単語認識プログラム

Country Status (5)

Country Link
US (1) US8208685B2 (ja)
EP (1) EP2138959B1 (ja)
JP (1) JP4672692B2 (ja)
KR (1) KR101016544B1 (ja)
WO (1) WO2008111399A1 (ja)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090208112A1 (en) * 2008-02-20 2009-08-20 Kabushiki Kaisha Toshiba Pattern recognition method, and storage medium which stores pattern recognition program
US8676001B2 (en) 2008-05-12 2014-03-18 Google Inc. Automatic discovery of popular landmarks
US8396287B2 (en) * 2009-05-15 2013-03-12 Google Inc. Landmarks from digital photo collections
US9183224B2 (en) * 2009-12-02 2015-11-10 Google Inc. Identifying matching canonical documents in response to a visual query
US9984131B2 (en) 2015-09-17 2018-05-29 International Business Machines Corporation Comparison of anonymized data
JP2018088116A (ja) * 2016-11-29 2018-06-07 キヤノン株式会社 情報処理装置、プログラム、情報処理方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05205109A (ja) * 1992-01-30 1993-08-13 Matsushita Electric Ind Co Ltd 文字認識装置
JPH06111079A (ja) * 1992-09-30 1994-04-22 Nippon Telegr & Teleph Corp <Ntt> 単語読み取り装置
JP2001283157A (ja) 2000-01-28 2001-10-12 Toshiba Corp 単語認識方法および単語認識プログラム

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0684006A (ja) * 1992-04-09 1994-03-25 Internatl Business Mach Corp <Ibm> オンライン手書き文字認識方法
JP3375766B2 (ja) * 1994-12-27 2003-02-10 松下電器産業株式会社 文字認識装置
US5963666A (en) * 1995-08-18 1999-10-05 International Business Machines Corporation Confusion matrix mediated word prediction
JP2000353215A (ja) * 1999-06-11 2000-12-19 Nec Corp 文字認識装置および文字認識プログラムを記録した記録媒体
US6847734B2 (en) 2000-01-28 2005-01-25 Kabushiki Kaisha Toshiba Word recognition method and storage medium that stores word recognition program
JP4744317B2 (ja) * 2006-02-16 2011-08-10 富士通株式会社 単語検索装置、単語検索方法、及びコンピュータプログラム
JP4686433B2 (ja) 2006-10-13 2011-05-25 株式会社東芝 単語認識方法および単語認識装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05205109A (ja) * 1992-01-30 1993-08-13 Matsushita Electric Ind Co Ltd 文字認識装置
JPH06111079A (ja) * 1992-09-30 1994-04-22 Nippon Telegr & Teleph Corp <Ntt> 単語読み取り装置
JP2001283157A (ja) 2000-01-28 2001-10-12 Toshiba Corp 単語認識方法および単語認識プログラム

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2138959A4

Also Published As

Publication number Publication date
KR101016544B1 (ko) 2011-02-24
EP2138959B1 (en) 2016-09-28
EP2138959A1 (en) 2009-12-30
EP2138959A4 (en) 2013-09-11
KR20090088304A (ko) 2009-08-19
US20080292186A1 (en) 2008-11-27
JP2008226030A (ja) 2008-09-25
US8208685B2 (en) 2012-06-26
JP4672692B2 (ja) 2011-04-20

Similar Documents

Publication Publication Date Title
WO2008111399A1 (ja) 単語認識方法および単語認識プログラム
CN108595410B (zh) 手写作文的自动批改方法及装置
CN105447206B (zh) 基于word2vec算法的新评论对象识别方法及系统
CN106815192B (zh) 模型训练方法及装置和语句情感识别方法及装置
US9342509B2 (en) Speech translation method and apparatus utilizing prosodic information
CN104166462B (zh) 一种文字的输入方法和系统
CN111046133A (zh) 基于图谱化知识库的问答方法、设备、存储介质及装置
CN101840699B (zh) 一种基于发音模型的语音质量评测方法
CN104809446B (zh) 基于校正手掌方向的掌纹感兴趣区域快速提取方法
CN101727902B (zh) 一种对语调进行评估的方法
ATE508453T1 (de) Generierung von grossen graphonem-einheiten mit kriterium gegenseitiger information für die sprachsynthese
WO2008137086A3 (en) Method and system for disambiguating informational objects
Layton et al. Recentred local profiles for authorship attribution
EP1752911A3 (en) Information processing method and information processing device
TW200737015A (en) Verification of authenticity
CN109192225B (zh) 语音情感识别和标注的方法及装置
CN106815197A (zh) 文本相似度的确定方法和装置
CN103020022A (zh) 一种基于改进信息熵特征的中文未登录词识别系统及方法
CN105280181B (zh) 一种语种识别模型的训练方法及语种识别方法
Das et al. An algorithm for Japanese character recognition
CN104915420B (zh) 知识库数据处理方法及系统
CN104142912A (zh) 一种精确的语料类别标注方法及装置
NZ589039A (en) Recognition of a word image with a plurality of characters by way of comparing two possible candidates based on an evaluation value
CN111159332A (zh) 一种基于bert的文本多意图识别方法
GB2429095B (en) Verification of authenticity

Legal Events

Date Code Title Description
REEP Request for entry into the european phase

Ref document number: 2008712055

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2008712055

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 1020087020028

Country of ref document: KR

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 08712055

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE