Neural versus Syntactic Recognition of Handwritten Numerals

  • Authors:

  • Luciana R. Veloso;João Marques de Carvalho

  • Affiliations:

  • -;-

  • Venue:
  • ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

This work concerns the analysis, implementation and evaluation of three different methods for handwritten numerical character recognition. The first approach uses a classifier based on syntactical analysis by decision tree.The other two methods consist of: (a) a conventional feed-forward Multi-layer neural network and (b) a recurrent neural network, for which the elements of the output layer are all interconnected. The CENPARMI data base was utilized for evaluation of the systems.