Presentation 1995/9/28
On-Line Kanji Character Recognition Using Stroke-based Affine Transformation
Toru WAKAHARA, Naoki NAKAJIMA, Sueharu MIYAHARA, Kazumi ODAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes an on-line Kanji character recognition algorithm using Stroke-based Affine Transformation (SAT). The first part of the algorithm determines one-to-one stroke correspondence between an input pattern and each reference pattern to absorb both stroke-number and stroke-order variations. The second part applies an optimal SAT to the input pattern to absorb handwriting distortion. The last part calculates the reinforced inter-pattern distance between the SAT-superimposed input pattern and the reference pattern. Experiments achieved high recognition rates of 98.4% for the square style and 96.0 % for the cursive style which were superior to those rates without SAT by 0.8 % and l.9%, respectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) On-line Kanji character recognition / handwriting distortion / stroke correspondence / affine transformation / least-squares method
Paper # PRU95-111
Date of Issue

Conference Information
Committee PRU
Conference Date 1995/9/28(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 Understanding (PRU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On-Line Kanji Character Recognition Using Stroke-based Affine Transformation
Sub Title (in English)
Keyword(1) On-line Kanji character recognition
Keyword(2) handwriting distortion
Keyword(3) stroke correspondence
Keyword(4) affine transformation
Keyword(5) least-squares method
1st Author's Name Toru WAKAHARA
1st Author's Affiliation NTT Human Interface Laboratories()
2nd Author's Name Naoki NAKAJIMA
2nd Author's Affiliation NTT Human Interface Laboratories
3rd Author's Name Sueharu MIYAHARA
3rd Author's Affiliation NTT Human Interface Laboratories
4th Author's Name Kazumi ODAKA
4th Author's Affiliation NTT Human Interface Laboratories
Date 1995/9/28
Paper # PRU95-111
Volume (vol) vol.95
Number (no) 278
Page pp.pp.-
#Pages 6
Date of Issue