Comparing Random Starts Local Search with Key Feature Matching
Abstract
A new variant on key feature object recognition is presented. It is applied to optimal matching problems involving 2D line segment models and data. A single criterion function ranks both key features and complete object model matches. Empirical studies suggest that the key feature algorithm has run times which are dramatically less than a more general random starts local search algorithm. However, they also show the key feature algorithm to be brittle: failing on some apparently simple problems, while local search appears to be robust.
Cite
Text
Beveridge et al. "Comparing Random Starts Local Search with Key Feature Matching." International Joint Conference on Artificial Intelligence, 1997.Markdown
[Beveridge et al. "Comparing Random Starts Local Search with Key Feature Matching." International Joint Conference on Artificial Intelligence, 1997.](https://mlanthology.org/ijcai/1997/beveridge1997ijcai-comparing/)BibTeX
@inproceedings{beveridge1997ijcai-comparing,
title = {{Comparing Random Starts Local Search with Key Feature Matching}},
author = {Beveridge, J. Ross and Graves, Christopher R. and Steinborn, Jim},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1997},
pages = {1476-1481},
url = {https://mlanthology.org/ijcai/1997/beveridge1997ijcai-comparing/}
}