Print Email Facebook Twitter Improving Image Registration Accuracy through User Interaction Title Improving Image Registration Accuracy through User Interaction Author Groen, Vincent (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Wiersma, R.T. (mentor) Marroquim, Ricardo (mentor) Eisemann, E. (mentor) Lofi, C. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-23 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. Subject Image RegistrationUser InteractionParameter Optimization To reference this document use: http://resolver.tudelft.nl/uuid:944abc2a-d060-4868-be69-b7bda7ebe57a Part of collection Student theses Document type bachelor thesis Rights © 2022 Vincent Groen Files PDF Research_Paper.pdf 7.99 MB Close viewer /islandora/object/uuid:944abc2a-d060-4868-be69-b7bda7ebe57a/datastream/OBJ/view