Presentation 1998/2/19
Handwritten Address Recognition using Dynamic Abstraction of Character Candidates
Hiroyuki ABE, Masato SUZUKI, Nei KATO, Yoshiaki NEMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In hand-written address recognition, it is diffucult to recognise low quality characters with accuracy. And conventional one-stage post-processing method has limitation when estimating address candidates. In this paper, we propose a two-stage method using dynamic abstraction of character candidates and re-recognition of characters. With making use of connections of segmentation position, this dynamic abstraction method makes it possible to find the correct address condidate even when an image of characeter is not a regular candidate. This paper describes these algorithm and evaluation results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) handwritten address recognition / abstraction of character candidates / post-processing / two-stage method
Paper #
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/2/19(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 Address Recognition using Dynamic Abstraction of Character Candidates
Sub Title (in English)
Keyword(1) handwritten address recognition
Keyword(2) abstraction of character candidates
Keyword(3) post-processing
Keyword(4) two-stage method
1st Author's Name Hiroyuki ABE
1st Author's Affiliation Graduate School of Information Sciences, TOHOKU University()
2nd Author's Name Masato SUZUKI
2nd Author's Affiliation Tokyo National College of Technology
3rd Author's Name Nei KATO
3rd Author's Affiliation Graduate School of Information Sciences, TOHOKU University
4th Author's Name Yoshiaki NEMOTO
4th Author's Affiliation Graduate School of Information Sciences, TOHOKU University
Date 1998/2/19
Paper #
Volume (vol) vol.97
Number (no) 558
Page pp.pp.-
#Pages 6
Date of Issue