PCA of 2D landmarks (relative warps)

This module is very similar to the standard PCA module, but with some added functionality for analyzing 2D landmark configurations. The expected data are specimens in rows, alternating x and y coordinates in columns. Procrustes standardization recommended.

The relative warps (principal components) are ordered according to importance, and the first and second warps are usually the most informative. Note that this module does a straightforward PCA of the landmarks, meaning that the affine component is included in the analysis.

The relative warps are visualized with vectors and/or thin-plate spline transformation grids. When you increase or decrease the score factor away from zero, the original landmark configuration and grid will be progressively deformed according to the selected relative warp. Vectors are drawn from the mean to the deformed (dot) landmark position.

Image may contain: Text, Line, Font, Screenshot, Design.

Published Aug. 31, 2020 8:29 PM - Last modified Aug. 31, 2020 8:33 PM