View in EDS PDF Full Text

Combination of statistical and neural classifiers for a high-accuracy recognition of large character sets.

Saved in:
Bibliographic Details
Title: Combination of statistical and neural classifiers for a high-accuracy recognition of large character sets.
Authors: Kimura, Yoshimasa1, Wakahara, Toru2, Tomono, Akira3
Source: Systems & Computers in Japan. 8/1/2005, Vol. 36 Issue 9, p97-107. 11p.
Subjects: Character sets (Data processing), Alphabet -- Data processing, Data processing of signs & symbols, Japanese character sets (Data processing), Artificial neural networks, Artificial intelligence
Abstract: In this paper the authors propose a method for high-accuracy recognition of large character sets using a new combination of a statistical method and neural networks. In their method, a hierarchical structure that has several neural networks arranged in a line after the statistical method is used. First, recognition using a statistical method is performed, and this represents the final result if the top candidate does not belong to a predefined set of similar characters. If it does, then the input character is discriminated in a neural network which designates the top candidate by determining the similar characters. The results are output as final results. The basic idea of this method is the functional division of a statistical method and neural networks, and the use of a neural network as determined by a statistical method. The results of recognizing 3201 character types including JIS-1 Kanji showed an improvement in the correct recognition rate due to the combined use of a statistical method and neural networks, thereby demonstrating the validity of the authors' approach. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(9): 97–107, 2005; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.20330 [ABSTRACT FROM AUTHOR]
Copyright of Systems & Computers in Japan is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 17331457
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Combination of statistical and neural classifiers for a high-accuracy recognition of large character sets.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kimura%2C+Yoshimasa%22">Kimura, Yoshimasa</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Wakahara%2C+Toru%22">Wakahara, Toru</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Tomono%2C+Akira%22">Tomono, Akira</searchLink><relatesTo>3</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Systems+%26+Computers+in+Japan%22">Systems & Computers in Japan</searchLink>. 8/1/2005, Vol. 36 Issue 9, p97-107. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Character+sets+%28Data+processing%29%22">Character sets (Data processing)</searchLink><br /><searchLink fieldCode="DE" term="%22Alphabet+--+Data+processing%22">Alphabet -- Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Data+processing+of+signs+%26+symbols%22">Data processing of signs & symbols</searchLink><br /><searchLink fieldCode="DE" term="%22Japanese+character+sets+%28Data+processing%29%22">Japanese character sets (Data processing)</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In this paper the authors propose a method for high-accuracy recognition of large character sets using a new combination of a statistical method and neural networks. In their method, a hierarchical structure that has several neural networks arranged in a line after the statistical method is used. First, recognition using a statistical method is performed, and this represents the final result if the top candidate does not belong to a predefined set of similar characters. If it does, then the input character is discriminated in a neural network which designates the top candidate by determining the similar characters. The results are output as final results. The basic idea of this method is the functional division of a statistical method and neural networks, and the use of a neural network as determined by a statistical method. The results of recognizing 3201 character types including JIS-1 Kanji showed an improvement in the correct recognition rate due to the combined use of a statistical method and neural networks, thereby demonstrating the validity of the authors' approach. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(9): 97–107, 2005; Published online in Wiley InterScience (<URL>www.interscience. wiley.com</URL>). DOI 10.1002/scj.20330 [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Systems & Computers in Japan is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=17331457
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/scj.20330
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 97
    Subjects:
      – SubjectFull: Character sets (Data processing)
        Type: general
      – SubjectFull: Alphabet -- Data processing
        Type: general
      – SubjectFull: Data processing of signs & symbols
        Type: general
      – SubjectFull: Japanese character sets (Data processing)
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
    Titles:
      – TitleFull: Combination of statistical and neural classifiers for a high-accuracy recognition of large character sets.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kimura, Yoshimasa
      – PersonEntity:
          Name:
            NameFull: Wakahara, Toru
      – PersonEntity:
          Name:
            NameFull: Tomono, Akira
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: 8/1/2005
              Type: published
              Y: 2005
          Identifiers:
            – Type: issn-print
              Value: 08821666
          Numbering:
            – Type: volume
              Value: 36
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Systems & Computers in Japan
              Type: main
ResultId 1