Comparing random starts local search with key feature matching

Authors:
J. Ross Beveridge;Christopher R. Graves;Jim Steinborn
Affiliations:
Computer Science Department, Colorado State University, Fort Collins, CO;Computer Science Department, Colorado State University, Fort Collins, CO;Computer Science Department, Colorado State University, Fort Collins, CO
Venue:
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Year:
1997

Citing 8
Cited 2

Extracting straight lines

IEEE Transactions on Pattern Analysis and Machine Intelligence
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Readings in computer vision: issues, problems, principles, and paradigms
Object recognition by computer: the role of geometric constraints

Object recognition by computer: the role of geometric constraints
Recognizing solid objects by alignment with an image

International Journal of Computer Vision
Local search algorithms for geometric object recognition: optimal correspondence and pose

Local search algorithms for geometric object recognition: optimal correspondence and pose
How Easy is Matching 2D Line Models Using Local Search?

IEEE Transactions on Pattern Analysis and Machine Intelligence
Perceptual Organization and Visual Recognition

Perceptual Organization and Visual Recognition
On the speed and accuracy of object recognition when using imperfect grouping

ISCV '95 Proceedings of the International Symposium on Computer Vision

Optimal 2D model matching using a messy genetic algorithm

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Simple algorithms for partial point set pattern matching under rigid motion

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

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.