A stochastic representation of cursive Chinese characters for on-line recognition

Tzren Ru Chou, Wen Tsuen Chen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, a stochastic representation of on-line Chinese characters of cursive style is proposed. A character in this representation is modeled by a sequence of concatenated stochastic curves, termed stochastic cubic Bézier curves (SCBC), with random noises. Furthermore, we also propose a curve alignment procedure to consistently match an input character with a stochastic reference one. Some classification experiments were performed. The stochastic approach is hardly sensitive to the characters with linked and degraded strokes; meanwhile, its recognition rate is higher than 95% even for deformed confusing characters.

Original languageEnglish
Pages (from-to)903-920
Number of pages18
JournalPattern Recognition
Volume30
Issue number6
DOIs
Publication statusPublished - 1997 Jan 1

Fingerprint

Experiments

Keywords

  • Bézier curves
  • De Casteljau algorithm
  • Dynamic programming
  • Elastic matching
  • Mahalanobis distance
  • Maximum likelihood estimation
  • On-line character recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

A stochastic representation of cursive Chinese characters for on-line recognition. / Chou, Tzren Ru; Chen, Wen Tsuen.

In: Pattern Recognition, Vol. 30, No. 6, 01.01.1997, p. 903-920.

Research output: Contribution to journalArticle

@article{291139c6eab94892b302503857dfb58b,
title = "A stochastic representation of cursive Chinese characters for on-line recognition",
abstract = "In this paper, a stochastic representation of on-line Chinese characters of cursive style is proposed. A character in this representation is modeled by a sequence of concatenated stochastic curves, termed stochastic cubic B{\'e}zier curves (SCBC), with random noises. Furthermore, we also propose a curve alignment procedure to consistently match an input character with a stochastic reference one. Some classification experiments were performed. The stochastic approach is hardly sensitive to the characters with linked and degraded strokes; meanwhile, its recognition rate is higher than 95{\%} even for deformed confusing characters.",
keywords = "B{\'e}zier curves, De Casteljau algorithm, Dynamic programming, Elastic matching, Mahalanobis distance, Maximum likelihood estimation, On-line character recognition",
author = "Chou, {Tzren Ru} and Chen, {Wen Tsuen}",
year = "1997",
month = "1",
day = "1",
doi = "10.1016/S0031-3203(96)00102-1",
language = "English",
volume = "30",
pages = "903--920",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "6",

}

TY - JOUR

T1 - A stochastic representation of cursive Chinese characters for on-line recognition

AU - Chou, Tzren Ru

AU - Chen, Wen Tsuen

PY - 1997/1/1

Y1 - 1997/1/1

N2 - In this paper, a stochastic representation of on-line Chinese characters of cursive style is proposed. A character in this representation is modeled by a sequence of concatenated stochastic curves, termed stochastic cubic Bézier curves (SCBC), with random noises. Furthermore, we also propose a curve alignment procedure to consistently match an input character with a stochastic reference one. Some classification experiments were performed. The stochastic approach is hardly sensitive to the characters with linked and degraded strokes; meanwhile, its recognition rate is higher than 95% even for deformed confusing characters.

AB - In this paper, a stochastic representation of on-line Chinese characters of cursive style is proposed. A character in this representation is modeled by a sequence of concatenated stochastic curves, termed stochastic cubic Bézier curves (SCBC), with random noises. Furthermore, we also propose a curve alignment procedure to consistently match an input character with a stochastic reference one. Some classification experiments were performed. The stochastic approach is hardly sensitive to the characters with linked and degraded strokes; meanwhile, its recognition rate is higher than 95% even for deformed confusing characters.

KW - Bézier curves

KW - De Casteljau algorithm

KW - Dynamic programming

KW - Elastic matching

KW - Mahalanobis distance

KW - Maximum likelihood estimation

KW - On-line character recognition

UR - http://www.scopus.com/inward/record.url?scp=0031165441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031165441&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(96)00102-1

DO - 10.1016/S0031-3203(96)00102-1

M3 - Article

AN - SCOPUS:0031165441

VL - 30

SP - 903

EP - 920

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 6

ER -