Recognition of multi-touch drawn sketches

  • Authors:
  • Michael Schmidt;Gerhard Weber

  • Affiliations:
  • Institute of Applied Science, Human-Computer Interaction, Dresden University of Technology, Dresden, Germany;Institute of Applied Science, Human-Computer Interaction, Dresden University of Technology, Dresden, Germany

  • Venue:
  • HCI'13 Proceedings of the 15th international conference on Human-Computer Interaction: interaction modalities and techniques - Volume Part IV
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present concepts and possible realizations for the classification of multi-touch drawn sketches. A gesture classifier is modified and integrated into a sketching tool. The applied routines are highly scalable and provide the possibilities of domain independent sketching. Classification rates are feasible without exploiting the full potential of the scheme. We demonstrate that the classifier is capable of identifying common basic primitives and gestures as well as complex drawings. Users define sketches per templates in their individual style and link them to constructed primitives. A pilot evaluation is conducted and results regarding sketching techniques of users and classification rates are discussed.