Presentation 2008-02-22
Chinese Character Recognition Based on Radical Parts and Application to Character Spotting
Gaku KITABAYASHI, Michio UMEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a radical area segmentation method to achieve Chinese character recognition focused on radical parts of characters, and apply this method to the realization of character spotting technique based on the features of segmented radical parts. All character patterns are devided linearly by using the projection profile in the radical candidate segmentation processing. In the radical decision segmentation, character patterns which contain conjunction or intrusion of elements are devided nonlinearly depending on the structure of Chinese characters. From the result of character spotting experiment, the correct spotting rate of average 96.28% is achieved to the specified 72 characters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) character recognition / chinese character recognition / character spotting / radical segmentation / weighted direction index histogram / autoassociative neural network
Paper # PRMU2007-244
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/2/14(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) Chinese Character Recognition Based on Radical Parts and Application to Character Spotting
Sub Title (in English)
Keyword(1) character recognition
Keyword(2) chinese character recognition
Keyword(3) character spotting
Keyword(4) radical segmentation
Keyword(5) weighted direction index histogram
Keyword(6) autoassociative neural network
1st Author's Name Gaku KITABAYASHI
1st Author's Affiliation Graduate School of Engineering, Osaka Electro-Communication University()
2nd Author's Name Michio UMEDA
2nd Author's Affiliation Graduate School of Engineering, Osaka Electro-Communication University
Date 2008-02-22
Paper # PRMU2007-244
Volume (vol) vol.107
Number (no) 491
Page pp.pp.-
#Pages 6
Date of Issue