Presentation 1998/2/20
Handwritten KANJI Recognition using Compund Discriminant Function
Takashi NAKAJIMA, Kazuhiro SAWA, Tetsushi WAKABAYASHI, Fumitaka KIMURA, Yasuji MIYAKE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose some new compound discriminant functions which are derived from the projection distance and the subspace method. The efficiency of the proposed method is evaluated by recognition experiments using handwritten KANJI character database ETL9B. The result shows that the proposed method achieves higher recognition rates than conventional method in both experiments for resembling two class recognition and general 3036 class recognition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) hadwritten character recognition / resembling characters / compound similarity / projection distance / ETL9B
Paper #
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/2/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Handwritten KANJI Recognition using Compund Discriminant Function
Sub Title (in English)
Keyword(1) hadwritten character recognition
Keyword(2) resembling characters
Keyword(3) compound similarity
Keyword(4) projection distance
Keyword(5) ETL9B
1st Author's Name Takashi NAKAJIMA
1st Author's Affiliation Faculty of Engineering, Mie University()
2nd Author's Name Kazuhiro SAWA
2nd Author's Affiliation Faculty of Engineering, Mie University
3rd Author's Name Tetsushi WAKABAYASHI
3rd Author's Affiliation Faculty of Engineering, Mie University
4th Author's Name Fumitaka KIMURA
4th Author's Affiliation Faculty of Engineering, Mie University
5th Author's Name Yasuji MIYAKE
5th Author's Affiliation Faculty of Engineering, Mie University
Date 1998/2/20
Paper #
Volume (vol) vol.97
Number (no) 559
Page pp.pp.-
#Pages 6
Date of Issue