Handwritten Word Recognition based on Structural Characteristics and Lexical Support

  • Authors:
  • E. Kavallieratou;K. Sgarbas;N. Fakotakis;G. Kokkinakis

  • Affiliations:
  • -;-;-;-

  • Venue:
  • ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper a handwritten recognition algorithmbased on structural characteristics, histograms andprofiles, is presented. The well-known horizontal andvertical histograms are used, in combination with thenewly introduced radial histogram, out-in radial and in-out radial profiles for representing 32x32 matrices ofcharacters, as 280-dimension vectors.The recognition process has been supported by alexical component based on dynamic acyclic FSAs(Finite-State-Automata).