Constructing Spatial Representations of Variable Detail for Sketch Recognition

Abstract

We describe a system which constructs spatial representations of sketches drawn by users. These representations are currently being used as the input for a spatial reasoning system which learns classifiers for performing sketch recognition. The spatial reasoning system requires representations at a level of detail sparser than that which the representation constructor normally builds. Therefore, we describe how the representation constructor ranks the expressions in its output so that the number of expressions in the representation can be decreased with minimal loss of information. We evaluate the overall system, showing that it is able to learn and utilize classifiers for complex sketches even when the representation size is sharply diminished.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2007
Accession Number
ADA470425

Entities

People

  • Andrew Lovett
  • Ken Forbus
  • Morteza Dehghani

Organizations

  • Northwestern University

Tags

DTIC Thesaurus Topics

  • Applied Computer Science
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Change Detection
  • Cognitive Science
  • Computer Science
  • Computer Vision
  • Heat Transfer
  • Hidden Markov Models
  • Images
  • Learning
  • Machine Learning
  • Markov Models
  • Photographic Images
  • Probability
  • Reasoning
  • Recognition

Fields of Study

  • Computer science

Readers

  • Mathematics or Statistics
  • Neural Network Machine Learning.
  • Systems Analysis and Design