ML Anthology

Learning Graph Models of Shape

Jakub Segen
ICML 1988 pp. 29-35
doi:10.1016/B978-0-934613-64-4.50008-6 /icml/1988/segen1988icml-learning/

Abstract

This paper describes an implemented system that learns structural models of shape from noisy image data. These models can be used to recognize deformable shapes with an arbitrary orientation, even if they are partially occluded. The representation used for instances and concepts of shape is a multilevel graph, whose vertices correspond to n-ary relations. The system exhibits two types of learning a constructive induction (involving learning from observations) used to discover relations, and learning from examples used to build the concept model. A concept model is constructed incrementally, by matching and merging graph instances. This process relies on a novel, very efficient graph matching method, that seeks a simplest representation of a graph. The performance of the system is demonstrated with real examples.

ICML Semantic Scholar

Cite

Text

Segen. "Learning Graph Models of Shape." International Conference on Machine Learning, 1988. doi:10.1016/B978-0-934613-64-4.50008-6

Markdown

[Segen. "Learning Graph Models of Shape." International Conference on Machine Learning, 1988.](https://mlanthology.org/icml/1988/segen1988icml-learning/) doi:10.1016/B978-0-934613-64-4.50008-6

BibTeX

@inproceedings{segen1988icml-learning,
  title     = {{Learning Graph Models of Shape}},
  author    = {Segen, Jakub},
  booktitle = {International Conference on Machine Learning},
  year      = {1988},
  pages     = {29-35},
  doi       = {10.1016/B978-0-934613-64-4.50008-6},
  url       = {https://mlanthology.org/icml/1988/segen1988icml-learning/}
}