Structural model constructing for optical handwritten character recognition

P. A. Khaustov, V. G. Spitsyn, E. I. Maksimova

Research output: Contribution to journalArticle

Abstract

The article is devoted to the development of the algorithms for optical handwritten character recognition based on the structural models constructing. The main advantage of these algorithms is the low requirement regarding the number of reference images. The one-pass approach to a thinning of the binary character representation has been proposed. This approach is based on the joint use of Zhang-Suen and Wu-Tsai algorithms. The effectiveness of the proposed approach is confirmed by the results of the experiments. The article includes the detailed description of the structural model constructing algorithm's steps. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database. Algorithms that could be used in case of limited reference images number were used for the comparison.

Original languageEnglish
Article number012006
JournalIOP Conference Series: Materials Science and Engineering
Volume173
Issue number1
DOIs
Publication statusPublished - 17 Feb 2017

Fingerprint

Optical character recognition
Processing
Experiments

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)

Cite this

Structural model constructing for optical handwritten character recognition. / Khaustov, P. A.; Spitsyn, V. G.; Maksimova, E. I.

In: IOP Conference Series: Materials Science and Engineering, Vol. 173, No. 1, 012006, 17.02.2017.

Research output: Contribution to journalArticle

@article{eaf462ac077143b3bda67bf4f3fb021d,
title = "Structural model constructing for optical handwritten character recognition",
abstract = "The article is devoted to the development of the algorithms for optical handwritten character recognition based on the structural models constructing. The main advantage of these algorithms is the low requirement regarding the number of reference images. The one-pass approach to a thinning of the binary character representation has been proposed. This approach is based on the joint use of Zhang-Suen and Wu-Tsai algorithms. The effectiveness of the proposed approach is confirmed by the results of the experiments. The article includes the detailed description of the structural model constructing algorithm's steps. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database. Algorithms that could be used in case of limited reference images number were used for the comparison.",
author = "Khaustov, {P. A.} and Spitsyn, {V. G.} and Maksimova, {E. I.}",
year = "2017",
month = "2",
day = "17",
doi = "10.1088/1757-899X/173/1/012006",
language = "English",
volume = "173",
journal = "IOP Conference Series: Materials Science and Engineering",
issn = "1757-8981",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Structural model constructing for optical handwritten character recognition

AU - Khaustov, P. A.

AU - Spitsyn, V. G.

AU - Maksimova, E. I.

PY - 2017/2/17

Y1 - 2017/2/17

N2 - The article is devoted to the development of the algorithms for optical handwritten character recognition based on the structural models constructing. The main advantage of these algorithms is the low requirement regarding the number of reference images. The one-pass approach to a thinning of the binary character representation has been proposed. This approach is based on the joint use of Zhang-Suen and Wu-Tsai algorithms. The effectiveness of the proposed approach is confirmed by the results of the experiments. The article includes the detailed description of the structural model constructing algorithm's steps. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database. Algorithms that could be used in case of limited reference images number were used for the comparison.

AB - The article is devoted to the development of the algorithms for optical handwritten character recognition based on the structural models constructing. The main advantage of these algorithms is the low requirement regarding the number of reference images. The one-pass approach to a thinning of the binary character representation has been proposed. This approach is based on the joint use of Zhang-Suen and Wu-Tsai algorithms. The effectiveness of the proposed approach is confirmed by the results of the experiments. The article includes the detailed description of the structural model constructing algorithm's steps. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database. Algorithms that could be used in case of limited reference images number were used for the comparison.

UR - http://www.scopus.com/inward/record.url?scp=85016219093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016219093&partnerID=8YFLogxK

U2 - 10.1088/1757-899X/173/1/012006

DO - 10.1088/1757-899X/173/1/012006

M3 - Article

AN - SCOPUS:85016219093

VL - 173

JO - IOP Conference Series: Materials Science and Engineering

JF - IOP Conference Series: Materials Science and Engineering

SN - 1757-8981

IS - 1

M1 - 012006

ER -