I don't believe my eyes!: geometric sketch recognition for a computer art tutorial

  • Authors:
  • D. Cummmings;F. Vides;T. Hammond

  • Affiliations:
  • Texas A&M University, TX;Texas A&M University, TX;Texas A&M University, TX

  • Venue:
  • Proceedings of the International Symposium on Sketch-Based Interfaces and Modeling
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Drawing is a common form of communication and a means of artistic expression. Many of us believe that the ability to draw accurate representations of objects is a skill that either comes naturally or is the result of hours of study or practice or both. As a result many people become intimidated when confronted with the task of drawing. Many books and websites have been developed to teach people step-by-step skills to draw various objects, but they lack the live feedback of a human examiner. We designed EyeSeeYou, a sketch recognition system that teaches users to draw eyes using a simple drawing technique. The system automatically evaluates the freehand drawn sketch of an eye at various stages during creation. We conducted frequent evaluations of the system in order to take an iterative development approach based on user feedback. Our system balances the flexibility of free-hand drawing with step-by-step instructions and realtime assessment. It also provides rigorous feedback to create a constructive learning environment to aid the user in improving her drawing. This paper describes the implementation details of the sketch recognition system. A similar implementation method could be used to provide sketching tutorials for a wide number of images.