Presentation 2006-02-24
A Method to Extract Strokes from Japanese Cursive Character Images using Computational Geometry
Kota ABE, Mamoru SHIBAYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method to extract strokes from Japanese cursive character images written with writing brushes. In our method, images are divided into two types of area; (1) complicated area which contains stroke intersections and contact points, and (2) remaining area, which is incontestably part of strokes. Then, stroke paths in complicated area are speculated using computational geometry techique. Stroke candidates can be obtained in likelihood order by evaluating combination of strokes which pass complicated area using evaluation functions. Applying the method against some character images taken from a Japanese cursive character dictionary confirmed that the method is promising. In this article, we will describe detail of the method and its experimental results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Stroke Extraction / Cursive Character / Computational Geometry
Paper # TL2005-79,PRMU2005-214
Date of Issue

Conference Information
Committee TL
Conference Date 2006/2/17(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 Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method to Extract Strokes from Japanese Cursive Character Images using Computational Geometry
Sub Title (in English)
Keyword(1) Stroke Extraction
Keyword(2) Cursive Character
Keyword(3) Computational Geometry
1st Author's Name Kota ABE
1st Author's Affiliation Graduate School for Creative Cities, Osaka City University()
2nd Author's Name Mamoru SHIBAYAMA
2nd Author's Affiliation Center for Southeast Asian Studies, Kyoto University
Date 2006-02-24
Paper # TL2005-79,PRMU2005-214
Volume (vol) vol.105
Number (no) 613
Page pp.pp.-
#Pages 6
Date of Issue