Sciweavers

Share
IJCAI
2007

Incremental Learning of Perceptual Categories for Open-Domain Sketch Recognition

8 years 11 months ago
Incremental Learning of Perceptual Categories for Open-Domain Sketch Recognition
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our system builds generalizations for categories of objects based upon previous sketches of those objects and uses those generalizations to classify new sketches. We represent sketches qualitatively because we believe qualitative information provides a level of description that abstracts away details that distract from classification, such as exact dimensions. Bayesian reasoning is used in building representations to deal with the inherent uncertainty in perception. Qualitative representations are compared using SME, a computational model of analogy and similarity that is supported by psychological evidence, including studies of perceptual similarity. We use SEQL to produce generalizations based on the common structure found by SME in different sketches of the same object. We report on the results of testing the s...
Andrew M. Lovett, Morteza Dehghani, Kenneth D. For
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2007
Where IJCAI
Authors Andrew M. Lovett, Morteza Dehghani, Kenneth D. Forbus
Comments (0)
books