Objective Functions for Feature Discrimination
Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Vision and Robotics. Pages 1596-1601.
Abstract
We propose and evaluate a class of objective functions that rank hypotheses for featu re labels. Our approach takes into account the representation cost alid quality of the shapes themselves, and balances the geometric requirements against the photometric evidence. This balance is essential for any system using underconstrained or generic feature models. We introduce examples of specific models allowing the actual computation of the terms in the objective function, and show how this framework leads naturally to control param eters that have a clear semantic meaning . We illustrate the properties of our objective functions on synthetic and real images.
@inproceedings{ijcai1989p254,
title = {Objective Functions for Feature Discrimination},
author = {Fua, Pascal and Hanson, Andrew J.},
booktitle = {Proceedings of the Eleventh International Joint Conference on
Artificial Intelligence, {IJCAI-89}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {N. S. Sridharan},
pages = {1596--1601},
year = {1989},
month = {8},
note = {Vision and Robotics},
url = {https://ijcai.org/proceedings/1989/254},
}
TY - CPAPER TI - Objective Functions for Feature Discrimination AU - Fua, Pascal AU - Hanson, Andrew J. T2 - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89 PB - International Joint Conferences on Artificial Intelligence PY - 1989 SP - 1596 EP - 1601 UR - https://ijcai.org/proceedings/1989/254 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
