Automatic character recognition based on graph theory: a new approach to automation

  • Authors:

  • Edinei Peres Legaspe;Wellington Sperandio Silva;Caio Fernando Fontana;Eduardo Mario Dias

  • Affiliations:

  • Power and Electric Automation Engineering Department, Escola Politécnica da Universidade de São Paulo, Brazil;Power and Electric Automation Engineering Department, Escola Politécnica da Universidade de São Paulo, Brazil;Power and Electric Automation Engineering Department, Escola Politécnica da Universidade de São Paulo, Brazil;Power and Electric Automation Engineering Department, Escola Politécnica da Universidade de São Paulo, Brazil

  • Venue:
  • CSCC'11 Proceedings of the 2nd international conference on Circuits, Systems, Communications & Computers
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The aim of this paper is to present a new method Optical Character Recognition (OCR). For it will be used for projections of images and the technique of Dijkstra's shortest path in graph-based structures can To validate the model presented in this work is implemented using software techniques commented above in the knowledge base organized around the Latin alphabet. We made several tests on the software and thus validating the proposed model. The presented method has the benefit that the training time of knowledge is much lower when compared to a neural network that performs the same operation.