ARG Based on Arcs and Segments to Improve the Symbol Recognition by Genetic Algorithm

  • Authors:
  • J. -P. Salmon;L. Wendling

  • Affiliations:
  • LORIA-UMR 7503, INPL, Vandoeuvre-lès-Nancy, France 54506;LORIA-UMR 7503, INPL, Vandoeuvre-lès-Nancy, France 54506

  • Venue:
  • Graphics Recognition. Recent Advances and New Opportunities
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

A genetic matching algorithm is extended to take into account primitive arcs in a pattern recognition process. Usually approaches based on segments are sensitive to over segmentation effects. Handling with more accurate description allows to improve the recognition by limiting the number of vertices to be matched and so to decrease processing time. Experimental studies using real data attest the robustness of the proposed method.