Large scale on-line handwritten Chinese character recognition using successor method based on stochastic regular grammar

Kazuhiro Kuroda, Ken Harada, Masafumi Hagiwara

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we propose an original method for the recognition of on-line handwritten Chinese characters using the successor method based on the stochastic regular grammar. We use Kohonen's self-organizing feature map for feature extraction to get optimal sets of prototypical waveforms of peaks from sample data automatically. The strings of symbols are converted into matrices using the stochastic successor method, and are analyzed by simple calculation between matrices. In order to symbolize and analyze input patterns efficiently and accurately in a large scale, we employ a hierarchical approach. Using unrestricted handwritten characters, we obtained 94.34% recognition rate for the test patterns.

Original languageEnglish
Pages (from-to)1307-1315
Number of pages9
JournalPattern Recognition
Volume32
Issue number8
Publication statusPublished - 1999 Aug

Fingerprint

Character recognition
Self organizing maps
Feature extraction

Keywords

  • Grammatical inference
  • Kohonen's self-organizing feature map
  • On-line handwriting recognition
  • Rough classification
  • Stochastic regular grammar
  • Subnetworks
  • Successor attribute matrix
  • Successor method

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Large scale on-line handwritten Chinese character recognition using successor method based on stochastic regular grammar. / Kuroda, Kazuhiro; Harada, Ken; Hagiwara, Masafumi.

In: Pattern Recognition, Vol. 32, No. 8, 08.1999, p. 1307-1315.

Research output: Contribution to journalArticle

@article{0bae310d6ab44435afff76a1137c49dd,
title = "Large scale on-line handwritten Chinese character recognition using successor method based on stochastic regular grammar",
abstract = "In this paper, we propose an original method for the recognition of on-line handwritten Chinese characters using the successor method based on the stochastic regular grammar. We use Kohonen's self-organizing feature map for feature extraction to get optimal sets of prototypical waveforms of peaks from sample data automatically. The strings of symbols are converted into matrices using the stochastic successor method, and are analyzed by simple calculation between matrices. In order to symbolize and analyze input patterns efficiently and accurately in a large scale, we employ a hierarchical approach. Using unrestricted handwritten characters, we obtained 94.34{\%} recognition rate for the test patterns.",
keywords = "Grammatical inference, Kohonen's self-organizing feature map, On-line handwriting recognition, Rough classification, Stochastic regular grammar, Subnetworks, Successor attribute matrix, Successor method",
author = "Kazuhiro Kuroda and Ken Harada and Masafumi Hagiwara",
year = "1999",
month = "8",
language = "English",
volume = "32",
pages = "1307--1315",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "8",

}

TY - JOUR

T1 - Large scale on-line handwritten Chinese character recognition using successor method based on stochastic regular grammar

AU - Kuroda, Kazuhiro

AU - Harada, Ken

AU - Hagiwara, Masafumi

PY - 1999/8

Y1 - 1999/8

N2 - In this paper, we propose an original method for the recognition of on-line handwritten Chinese characters using the successor method based on the stochastic regular grammar. We use Kohonen's self-organizing feature map for feature extraction to get optimal sets of prototypical waveforms of peaks from sample data automatically. The strings of symbols are converted into matrices using the stochastic successor method, and are analyzed by simple calculation between matrices. In order to symbolize and analyze input patterns efficiently and accurately in a large scale, we employ a hierarchical approach. Using unrestricted handwritten characters, we obtained 94.34% recognition rate for the test patterns.

AB - In this paper, we propose an original method for the recognition of on-line handwritten Chinese characters using the successor method based on the stochastic regular grammar. We use Kohonen's self-organizing feature map for feature extraction to get optimal sets of prototypical waveforms of peaks from sample data automatically. The strings of symbols are converted into matrices using the stochastic successor method, and are analyzed by simple calculation between matrices. In order to symbolize and analyze input patterns efficiently and accurately in a large scale, we employ a hierarchical approach. Using unrestricted handwritten characters, we obtained 94.34% recognition rate for the test patterns.

KW - Grammatical inference

KW - Kohonen's self-organizing feature map

KW - On-line handwriting recognition

KW - Rough classification

KW - Stochastic regular grammar

KW - Subnetworks

KW - Successor attribute matrix

KW - Successor method

UR - http://www.scopus.com/inward/record.url?scp=0032653337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032653337&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0032653337

VL - 32

SP - 1307

EP - 1315

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 8

ER -