Algorithm for optical handwritten characters recognition based on structural components extraction

Podrobná bibliografie
Parent link:11th International Forum on Strategic Technology (IFOST 2016): 1-3 June 2016, Novosibirsk, Russiain/ Novosibirsk State Technical University.— , 2016
Pt. 1.— 2017.— [P. 355-358]
Hlavní autor: Khaustov P. A. Pavel Aleksandrovich
Korporativní autor: Национальный исследовательский Томский политехнический университет (ТПУ) Институт кибернетики (ИК)
Další autoři: Spitsyn V. G. Vladimir Grigorievich, Maksimova E. I.
Shrnutí:Title screen
The algorithm for character topology composition has been proposed. Metrics for character graphs comparison has been suggested. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database and writing characters examples from the forms of a unified state exam.
Режим доступа: по договору с организацией-держателем ресурса
Vydáno: 2017
Edice:Information and communication technologies
Témata:
On-line přístup:http://dx.doi.org/10.1109/IFOST.2016.7884126
Médium: Elektronický zdroj Kapitola
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=654563

Podobné jednotky