Presentation 1997/3/18
An Off-line Handwritten Character Recognition Method based on a Dynamic Model
Takeshi NAGASAKI, Takayoshi YAMAMOTO, Masaki NAKAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes an off-line handwritten character recognition method based on a dynamic model. As a dynamic model of character patterns. a string-like elastic body consisting of mass points and springs has been adopted. We call this model an "Elastic stroke model" . Dictionary patterns formed with the elastic stroke model are matched with potential field made from an input pattern. The matching process is computed by dynamic programming. Pattern similarity is measured by the energy. As a result of experiments on 46Hiragana characters. we concluded that this method has sufficient potential to recognize handwritten characters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) off-line character recognition / dynamic relaxation / DP / elastic stroke model
Paper # PRMU96-185
Date of Issue

Conference Information
Committee PRMU
Conference Date 1997/3/18(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) An Off-line Handwritten Character Recognition Method based on a Dynamic Model
Sub Title (in English)
Keyword(1) off-line character recognition
Keyword(2) dynamic relaxation
Keyword(3) DP
Keyword(4) elastic stroke model
1st Author's Name Takeshi NAGASAKI
1st Author's Affiliation Department of Computer Science Tokyo University of Agriculture and Technology()
2nd Author's Name Takayoshi YAMAMOTO
2nd Author's Affiliation Department of Computer Science Tokyo University of Agriculture and Technology
3rd Author's Name Masaki NAKAGAWA
3rd Author's Affiliation Department of Computer Science Tokyo University of Agriculture and Technology
Date 1997/3/18
Paper # PRMU96-185
Volume (vol) vol.96
Number (no) 598
Page pp.pp.-
#Pages 6
Date of Issue