Dynamically Constructed Bayes Nets for Multi-Domain Sketch Understanding
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1407-1411.
Abstract
This paper presents a novel form of dynamically constructed Bayes net, developed for multi-domain sketch recognition. Our sketch recognition engine integrates shape information and domain knowledge to improve recognition accuracy across a variety of domains using an extendible, hierarchical approach. Our Bayes net framework integrates the influence of stroke data and domain-specific context in recognition, enabling our recognition engine to handle noisy input. We illustrate this behavior with qualitative and quantitative results in two domains: hand-drawn family trees and circuits.
@inproceedings{ijcai2005p198,
title = {Dynamically Constructed Bayes Nets for Multi-Domain Sketch Understanding},
author = {Alvarado, Christine and Davis, Randall},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1407--1411},
year = {2005},
url = {https://ijcai.org/proceedings/2005/198},
}
TY - CPAPER TI - Dynamically Constructed Bayes Nets for Multi-Domain Sketch Understanding AU - Alvarado, Christine AU - Davis, Randall T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1407 EP - 1411 UR - https://ijcai.org/proceedings/2005/198 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
