Comparing Random Starts Local Search with Key Feature Matching
Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence. Vision. Pages 1476-1480.
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.
@inproceedings{ijcai1997p212,
title = {Comparing Random Starts Local Search with Key Feature Matching},
author = {Beveridge, J. Ross and Graves, Christopher R. and Steinborn, Jim},
booktitle = {Proceedings of the Fifteenth International Joint Conference on
Artificial Intelligence, {IJCAI-97}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Martha E. Pollack},
pages = {1476--1480},
year = {1997},
note = {Vision},
url = {https://ijcai.org/proceedings/1997/212},
}
TY - CPAPER TI - Comparing Random Starts Local Search with Key Feature Matching AU - Beveridge, J. Ross AU - Graves, Christopher R. AU - Steinborn, Jim T2 - Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97 PB - International Joint Conferences on Artificial Intelligence PY - 1997 SP - 1476 EP - 1480 UR - https://ijcai.org/proceedings/1997/212 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
