The structure-mapping engine: algorithm and examples
Artificial Intelligence
Perceptually based learning of shape descriptions for sketch recognition
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Transforming between propositions and features: bridging the gap
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Dynamically constructed Bayes nets for multi-domain sketch understanding
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Recognizing and simulating sketched logic circuits
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Open-ended category learning for language acquisition
Connection Science - Language and Robots
A complete label set for 3D-sketch labeling
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
Hi-index | 0.01 |
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for open-domain 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 system on a corpus of sketches of everyday objects, drawn by ten different people.