An Eigendecomposition Approach to Weighted Graph Matching Problems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature-based correspondence: an eigenvector approach
Image and Vision Computing - Special issue: BMVC 1991
Structural Matching by Discrete Relaxation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonlinear component analysis as a kernel eigenvalue problem
Neural Computation
Kernel PCA and de-noising in feature spaces
Proceedings of the 1998 conference on Advances in neural information processing systems II
Learning Compatibility Coefficients for Relaxation Labeling Processes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Modal Matching for Correspondence and Recognition
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)
Generating Semantic Descriptions From Drawings of Scenes With Shadows
Generating Semantic Descriptions From Drawings of Scenes With Shadows
Correspondence Matching with Modal Clusters
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Eigenspace Projection Clustering Method for Inexact Graph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
Versatile spectral methods for point set matching
Pattern Recognition Letters
Using diagonals of orthogonal projection matrices for affine invariant contour matching
Image and Vision Computing
Pattern analysis with graphs: Parallel work at Bern and York
Pattern Recognition Letters
Robust point pattern matching based on spectral context
Pattern Recognition
Hi-index | 0.01 |
This paper investigates spectral approaches to the problem of point pattern matching. We make two contributions. First, we consider rigid point-set alignment. Here we show how kernel principal components analysis (kernel PCA) can be effectively used for solving the rigid point correspondence matching problem when the point-sets are subject to outliers and random position jitter. Specifically, we show how the point- proximity matrix can be kernelised, and spectral correspondence matching transformed into one of kernel PCA. Second, we turn our attention to the matching of articulated point-sets. Here we show label consistency constraints can be incorporated into definition of the point proximity matrix. The new methods are compared to those of Shapiro and Brady and Scott and Longuet-Higgins, together with multidimensional scaling. We provide experiments on both synthetic data and real world data.