Structural model constructing for optical handwritten character recognition

Bibliographic Details
Parent link:IOP Conference Series: Materials Science and Engineering
Vol. 173 : Mathematical Models and their Applications 2016.— 2017.— 012006, 9 p.]
Main Author: Khaustov P. A. Pavel Aleksandrovich
Corporate Author: Национальный исследовательский Томский политехнический университет (ТПУ) Институт кибернетики (ИК) Кафедра информационных систем и технологий (ИСТ)
Other Authors: Spitsyn V. G. Vladimir Grigorievich, Maksimova E. I. Elena Ivanovna
Summary:Title screen
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.
Published: 2017
Subjects:
Online Access:http://dx.doi.org/10.1088/1757-899X/173/1/012006
http://earchive.tpu.ru/handle/11683/45806
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=654643
Description
Summary:Title screen
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.
DOI:10.1088/1757-899X/173/1/012006