We apply and evaluate machine learning methods to obtain information purely from the tomographic projections of an image. We design and implement discrete tomographic reconstruction methods that can exploit the knowledge obtained in this way.

The aim of this project is to improve the well-known methods of continuous and discrete tomography. We study image processing methods that can be applied directly on the projections to improve reconstruction quality. We improve techniques to measure the quality of the reconstructed images, and develop image reconstruction methods based on parallel processing using GPUs. We also investigate which are the most valuable projections, if the reconstruction is performed from just a few of them.

The goal of the project is to develop efficient image acquisition methods to gain visual information from incorrect, noisy, and uncertain projections.

New approaches in Discrete Tomography are investigated. Studies are concentrating on absorbed projections, fan-beam geometry, new geometrical properties of discrete sets. Besides, new application fields (such as neutron radiography) are studied.

Theoretical aspects of main problems in Discrete Tomography are studied such as existence, consistency, and reconstruction under several assumptions. Efficient reconstruction algorithms are also developed by incorporating prior knowledge into the reconstruction.