Synthesizing handwritten characters using naturalness learning

Ján Dolinský, Hideyuki Takagi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

In this paper we show how to synthesize handwritten characters using a proposed system for naturalness learning. We begin by explaining what we mean by naturalness and then show that in many characters, certain properties of font character strokes does not have a linear relation with this naturalness. This observation inspires the idea of using nonlinear techniques to model the naturalness in order to generate handwriting of a unique, personalized, form. Several techniques for achieving this were tested. Surprisingly, RNN with a recurrent output layer performed the best at generating characters very similar to a person's handwriting.

Original languageEnglish
Title of host publicationICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings
Pages101-106
Number of pages6
DOIs
Publication statusPublished - Dec 1 2007
EventICCC 2007 - 5th IEEE International Conference on Computational Cybernetics - Gammarth, Tunisia
Duration: Oct 19 2007Oct 21 2007

Publication series

NameICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings

Other

OtherICCC 2007 - 5th IEEE International Conference on Computational Cybernetics
CountryTunisia
CityGammarth
Period10/19/0710/21/07

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering

Cite this

Dolinský, J., & Takagi, H. (2007). Synthesizing handwritten characters using naturalness learning. In ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings (pp. 101-106). [4402023] (ICCC 2007 - 5th IEEE International Conference on Computational Cybernetics, Proceedings). https://doi.org/10.1109/ICCCYB.2007.4402023