A Matching Scheme to Enhance Performance Evaluation of Raster-to-Vector Conversion Algorithms

  • Authors:
  • Xavier Hilaire

  • 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

This paper deals with performance evaluation of raster-to-vector conversion algorithms. We briefly review the pastwork, and focus our attention on a method proposed byPhillips and Chhabra [6]. We show that the matching algorithmused in their method can be improved by introducingnew metrics and reformulating the problem as a combinatorialoptimization scheme. Improvements brought by ourapproach are the reduction of the number of utilized thresholdsto one, and a gain of stability in the obtained results.We also propose an algorithmto solve the scheme, and comparethe evaluation results obtained with both methods onreal CAD drawings.