Evaluation of Models and Non-Rigid Registration

April 22nd, 2005

Why Evaluate?

Why Evaluate?

Because certain methods neglect available information

Overview

Non-Rigid Registration

Non-Rigid Registration

Statistical Models

Statistical Models

Statistical Models

Finding Correspondences

Finding Correspondences

Where is a corresponding point in the volume?

Picture from Johan Montagnat, INRIA

Finding Correspondences

Finding Correspondences

Finding Correspondences - ctd.

Finding Correspondences - ctd.

Finding Correspondences - ctd.

Model Construction

Non-Rigid Registration «-» Modelling

Degradation of Registration


0 to 5 CPS warps perturbing the correct solution.
Shown is the first mode of the model, ±2.5 SD

Evaluation Method - Models


Model of the registered images and synthesis from the model

Evaluation Method - Abstraction


A hyperspace representation where 'clouds' of images overlap

Evaluation Method - Derivations


Calculating Specificity and Generalisation ability

Measuring Distance

Measuring Distance - Shuffle Distance

Validation of the Method


As correspondences degrade, so does Generalisability (low values are good)

Validation of the Method


As correspondences degrade, so does Specificity

Validation of the Method


Investigate measures most sensitive to change

Validation of the Method


Shuffle distances covering a large region are sensitive to differences

Validation of the Method


The choice of shuffle distance radius becomes an efficiency vs. performance trade-off

Evaluation of Registration

Registration Algorithms - Comparison


Group-wise methods surpass pair-wise regardless of the expressiveness of the model used

Visual Comparison

Summary

Conclusions