Table of contents

A Generic Method for Evaluating Appearance Models and Assessing the Accuracy of NRR

Overview

Motivation

Existing Methods of Assessment

Model-Based Assessment

Model-based Framework

Building an Appearance Model

Slide 8

Training and Synthetic Images

Slide 10

Slide 11

Slide 12

Slide 13

Slide 14

Slide 15

Slide 16

Slide 17

Slide 18

Slide 19

Slide 20

Slide 21

Slide 22

Slide 23

Slide 24

Slide 25

Slide 26

Model Quality

Measuring Inter-Image Distance

Shuffle Distance

Varying Shuffle Radius

Validation Experiments

Experimental Design

Brain Data

Perturbation Framework

Examples of Perturbed Images

Results – Generalised Overlap

Results – Model-Based

Results – Comparison

Results – Sensitivities

Further Tests – Noise

Practical Application – NRR Benchmark

Practical Application

Practical Application - Results

Extension to 3-D

Conclusions

Author: Roy Schestowitz

E-mail: r at schestowitz dot com

Homepage: http://schestowitz.com/

Further information:
Exported from OpenOffice 2