Improving correspondence matching using label consistency constraints

Authors:
Hongfang Wang;Edwin R. Hancock
Affiliations:
Dept. of Computer Science, University of York, Heslington, York, UK;Dept. of Computer Science, University of York, Heslington, York, UK
Venue:
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
Year:
2005

Citing 6
Cited 0

Feature-based correspondence: an eigenvector approach

Image and Vision Computing - Special issue: BMVC 1991
Shape and motion from image streams under orthography: a factorization method

International Journal of Computer Vision
Structural Matching by Discrete Relaxation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
Learning Compatibility Coefficients for Relaxation Labeling Processes

IEEE Transactions on Pattern Analysis and Machine Intelligence
A direct method for stereo correspondence based on singular value decomposition

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we demonstrate how to embed label consistency constraints into point correspondence matching. We make two contributions. First, we show how the point proximity matrix can be incorporated into the support function for probabilistic relaxation. Second we show how the label probabilities delivered by relaxation labelling can be used to gate the kernel matrix for articulated point pattern matching. The method is evaluated on synthetic and real-world data, where the label compatibility process is demonstrated to improve the correspondence process.