Object Recognition Based on Visual Grammars and Bayesian Networks
Abstract
A novel proposal for object recognition based on relational grammars and Bayesian Networks is presented. Based on this grammar an object is represented as a hierarchy of features and spatial relations. This representation is transformed to a Bayesian network structure which parameters are learned from examples. Thus, recognition is based on probabilistic inference in the Bayesian network representation. Preliminary results in modeling natural objects are presented.
Cite
Text
Ruiz and Sucar. "Object Recognition Based on Visual Grammars and Bayesian Networks." International Joint Conference on Artificial Intelligence, 2013.Markdown
[Ruiz and Sucar. "Object Recognition Based on Visual Grammars and Bayesian Networks." International Joint Conference on Artificial Intelligence, 2013.](https://mlanthology.org/ijcai/2013/ruiz2013ijcai-object/)BibTeX
@inproceedings{ruiz2013ijcai-object,
title = {{Object Recognition Based on Visual Grammars and Bayesian Networks}},
author = {Ruiz, Elias and Sucar, Luis Enrique},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2013},
pages = {3241-3242},
url = {https://mlanthology.org/ijcai/2013/ruiz2013ijcai-object/}
}