Improving Image Registration Accuracy through User Interaction
V. Groen (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Ruben Wiersma – Mentor (TU Delft - Computer Graphics and Visualisation)
Ricardo Guerra Marroquim – Mentor (TU Delft - Computer Graphics and Visualisation)
E. Eisemann – Mentor (TU Delft - Computer Graphics and Visualisation)
C. Lofi – Graduation committee member (TU Delft - Web Information Systems)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The current state-of-the-art image alignment techniques and their input parameters are often unintuitive to those without the required background knowledge.
This work aims to provide users with a graphical user interface through which they can intuitively influence the parameters and results of the algorithm by excluding certain areas from the images.
The application is also capable of automatically optimizing the parameters of the underlying registration algorithm.
Experimental results indicate that the automatic parameter optimization results in alignments at least as good as the default parameters, but that the introduced user interaction does not provide any major benefits.