A Trainable System for Recognizing Diagrammatic Sketch Languages

  • Authors:
  • Gennaro Costagliola;Vincenzo Deufemia;Michele Risi

  • Affiliations:
  • Università di Salerno;Università di Salerno;Università di Salerno

  • Venue:
  • VLHCC '05 Proceedings of the 2005 IEEE Symposium on Visual Languages and Human-Centric Computing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we propose an approach for constructing sketch parsers whose recognition accuracy and speed is significantly improved by acquiring information on the userýs sketching style during a training phase. The construction process consists in specifying a sketch grammar description of the language syntax, automatically generating a parser from such specification, and let the user train the recognition system on a set of sketch sentences.