---
title: "Comparing Random Starts Local Search with Key Feature Matching"
authors:
  - "J. Ross Beveridge"
  - "Christopher R. Graves"
  - "Jim Steinborn"
doi: ""
url: "https://ijcai.org/proceedings/1997/212"
pdf: "https://ijcai.org/proceedings/1997/0212.pdf"
venue: "Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence"
year: 1997
pages: "1476-1480"
track: "Vision"
keywords:
---

# Comparing Random Starts Local Search with Key Feature Matching

J. Ross Beveridge, Christopher R. Graves, Jim Steinborn

*Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence*, 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.