Multivariate aspects of shape theory (Q688390)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Multivariate aspects of shape theory |
scientific article |
Statements
Multivariate aspects of shape theory (English)
0 references
2 June 1994
0 references
Let \({\mathbf X}: N\times K\) be a matrix presenting the geometrical figure comprising \(N\) landmark, or labeled, points in \(R^ k\). The shape of \({\mathbf X}\) is the figure with translation, orientation and scale removed. The authors placed shape theory in the setting of noncentral multivariable analysis and provided a comprehensive view of shape distributions when landmark coordinates are Gaussian distributed. The standard techniques of multivariate analysis are applied to deal with the statistical analysis of shape although there are some differences between their work and standard multivariate theory. Their work includes some new results in all dimensions to the size-and-shape distribution, and also investigates some inference problems for shape.
0 references
Gaussian model
0 references
shape theory
0 references
noncentral multivariable analysis
0 references
shape distributions
0 references
landmark coordinates
0 references
size-and-shape distribution
0 references
inference problems
0 references