Discrete tomography (DT) is a set of tools for reconstructing the inner structure of objects consisting of only few different homogeneous materials. We propose a new method for multivalued DT, which performs the reconstruction as an energy minimisation task. For this algorithm, we define an energy function that can mathematically formulate the reconstruction task, and design a novel optimisation process for approximating the minima of this energy function. We validate the algorithm by comparing its performance with other cutting-edge reconstruction algorithms from the literature. We show that our method can compete with the currently used reconstruction techniques and under certain circumstances (e.g. with a low number of projections, or when the projection data are affected by random noise) it can even outperform them.

PB - Taylor&Francis VL - 3 IS - 2 ER - TY - CONF T1 - Időskori makula degeneráció kvantitatív jellemzése SD-OCT képek automatikus elemzésével T2 - A XXVIII. Neumann Kollokvium konferencia-kiadványa Y1 - 2015 A1 - László Gábor Varga A1 - Melinda Katona A1 - Tamás Grósz A1 - József Dombi A1 - Attila Kovács A1 - Rózsa Dégi A1 - László G Nyúl JF - A XXVIII. Neumann Kollokvium konferencia-kiadványa PB - Neumann János Számítógép-tudományi Társaság CY - Veszprém, Hungary ER - TY - CHAP T1 - Képfeldolgozás a szegedi informatikus-képzésben T2 - Informatika a felsőoktatásban 2014 Y1 - 2014 A1 - Péter Balázs A1 - Endre Katona A1 - Zoltan Kato A1 - Antal Nagy A1 - Gábor Németh A1 - László Gábor Nyúl A1 - Kálmán Palágyi A1 - Attila Tanacs A1 - László Gábor Varga ED - Roland Kunkli ED - Ildikó Papp ED - Edéné Rutkovszky JF - Informatika a felsőoktatásban 2014 PB - University of Debrecen CY - Debrecen, Hungary ER - TY - JOUR T1 - Local and global uncertainty in binary tomographic reconstruction JF - COMPUTER VISION AND IMAGE UNDERSTANDING Y1 - 2014 A1 - László Gábor Varga A1 - László Gábor Nyúl A1 - Antal Nagy A1 - Péter Balázs AB -In binary tomography the goal is to reconstruct the innerstructure of homogeneous objects from their projections. This is usually required from a low number of projections, which are also likely to be aﬀected by noise and measurement errors. In general, the distorted and incomplete projection data holds insuﬃcient information for the correct reconstruction of the original object. In this paper, we describe two methods for approximating the local uncertainty of the reconstructions, i.e., identifying how the information stored in the projections determine each part of the reconstructed image. These methods can measure the uncertainty of the reconstruction without any knowledge from the original object itself. Moreover, we provide a global uncertainty measure that can assess the information content of a projection set and predict the error to be expected in the reconstruction of a homogeneous object. We also give an experimental evaluation of our proposed methods, mention some of their possible applications, and describe how the uncertainty measure can be used to improve the performance of the DART reconstruction algorithm.

SN - 1077-3142 N1 - Art. No.: S1077-3142(14)00117-9doi: 10.1016/j.cviu.2014.05.006Article in Press JO - COMPUT VIS IMAGE UND ER - TY - CONF T1 - Gradiens módszerek automatikus súlyozásán alapuló diszkrét tomográfiai eljárás T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 Y1 - 2013 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy ED - László Czúni JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 PB - NJSZT-KÉPAF CY - Veszprém ER - TY - CHAP T1 - Local uncertainty in binary tomographic reconstruction T2 - Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA 2013) Y1 - 2013 A1 - László Gábor Varga A1 - László Gábor Nyúl A1 - Antal Nagy A1 - Péter Balázs ED - Martin Kampel AB -We describe a new approach for the uncertainty problem arisingin the field of discrete tomography, when the low number of projections does not hold enough information for an accurate, and reliable reconstruction. In this case the lack of information results in uncertain parts on the reconstructed image which are not determined by the projections and cannot be reliably reconstructed without additional information. We provide a method that can approximate this local uncertainty of reconstructions, and show how each pixel of the reconstructed image is determined by a set of given projections. We also give experimental results for validating our approach.

JF - Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA 2013) PB - IASTED - Acta Press CY - Calgary N1 - ScopusID: 84876584488doi: 10.2316/P.2013.798-067 ER - TY - CHAP T1 - An energy minimization reconstruction algorithm for multivalued discrete tomography T2 - Computational Modelling of Objects Represented in Images: Fundamentals, Methods and Applications III Y1 - 2012 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy ED - Paolo Di Giamberardino ED - Daniela Iacoviello ED - Renato M Natal Jorge ED - Joao Manuel R S Taveres AB -We propose a new algorithm for multivalued discrete tomography, that reconstructs images from few projections by approximating the minimum of a suitably constructed energy function with a deterministic optimization method. We also compare the proposed algorithm to other reconstruction techniques on software phantom images, in order to prove its applicability.

JF - Computational Modelling of Objects Represented in Images: Fundamentals, Methods and Applications III PB - CRC Press - Taylor and Frances Group CY - London ER - TY - Generic T1 - A novel optimization-based reconstruction algorithm for multivalued discrete tomography Y1 - 2012 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy JF - Conference of PhD students in computer science. Volume of extended abstracts. PB - University of Szeged, Institute of Informatics CY - Szeged ER - TY - CONF T1 - An optimization-based reconstruction algorithm for multivalued discrete tomography T2 - Veszprém Optimization Conference: Advanced Algorithms (Vocal) Y1 - 2012 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy JF - Veszprém Optimization Conference: Advanced Algorithms (Vocal) PB - University of Pannonia CY - Veszprém ER - TY - JOUR T1 - Direction-dependency of binary tomographic reconstruction algorithms JF - GRAPHICAL MODELS Y1 - 2011 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy AB -In this work we study the relation between the quality of a binary tomographic reconstruction and the choice of angles of the projections. We conduct experiments on a set of software phantoms by reconstructing them from different projection sets using three different discrete tomography reconstruction algorithms, and compare the accuracy of the corresponding reconstructions with suitable approaches. To validate our results for possible real-world applications, we conduct the experiments by adding random noise of different characteristics to the simulated projection data, and by applying small topological changes on the phantom images as well. In addition, we also discuss some consequences of the angle-selection dependency and possible practical applications arising from the field of non-destructive testing, too.

VL - 73 SN - 1524-0703 IS - 6 N1 - UT: 000296999100028ScopusID: 80054709026doi: 10.1016/j.gmod.2011.06.006 JO - GRAPH MODELS ER - TY - JOUR T1 - Projection selection dependency in binary tomography JF - ACTA CYBERNETICA-SZEGED Y1 - 2011 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy AB -It has already been shown that the choice of projection angles can significantly influence the quality of reconstructions in discrete tomography. In this contribution we summarize and extend the previous results by explaining and demonstrating tile effects of projection selection dependency, in a set of experimental software tests. We perform reconstructions of software phantoms, by using different binary tomography reconstruction algorithms, from different equiangular and non-equiangular projections sets, under various conditions (i.e., when the objects to be reconstructed undergo slight topological changes, or the projection data is affected by noise) and compare the results with suitable approaches. Based on our observations, we reveal regularities in the resulting data and discuss possible consequences of such projection selection dependency in binary tomography.

PB - University of Szeged, Institute of Informatics CY - Szeged VL - 20 SN - 0324-721X IS - 1 N1 - ScopusID: 79960679541 JO - ACTA CYBERN-SZEGED ER - TY - CONF T1 - Vetületi irányfüggőség a bináris tomográfiában T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged ER - TY - CHAP T1 - Direction-dependency of a binary tomographic reconstruction algorithm T2 - Computational Modeling of Objects Represented in Images Y1 - 2010 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy ED - Reneta P Barneva ED - Valentin E Brimkov ED - Herbert A Hauptman ED - Renato M Natal Jorge ED - João Manuel R S Tavares AB -

We study how the quality of an image reconstructed by a binary tomographic algorithm depends on the direction of the observed object in the scanner, if only a few projections are available. To do so we conduct experiments on a set of software phantoms by reconstructing them form different projection sets using an algorithm based on D.C. programming (a method for minimizing the difference of convex functions), and compare the accuracy of the corresponding reconstructions by two suitable approaches. Based on the experiments, we discuss consequences on applications arising from the field of non-destructive testing, as well.

JF - Computational Modeling of Objects Represented in Images T3 - Lecture Notes in Computer Science PB - Springer Verlag CY - Buffalo, NY, USA SN - 978-3-642-12711-3 N1 - UT: 000279020400022ScopusID: 77952365308doi: 10.1007/978-3-642-12712-0_22 JO - LNCS ER - TY - CONF T1 - Object rotation effects on binary tomographic reconstruction T2 - Conference of PhD Students in Computer Science. Volume of Extended Abstracts Y1 - 2010 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy JF - Conference of PhD Students in Computer Science. Volume of Extended Abstracts PB - University of Szeged CY - Szeged, Hungary ER - TY - CHAP T1 - Projection selection algorithms for discrete tomography T2 - Advanced Concepts for Intelligent Vision Systems Y1 - 2010 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy ED - Jacques Blanc-Talon ED - Don Bone ED - Wilfried Philips ED - Dan Popescu ED - Paul Scheunders JF - Advanced Concepts for Intelligent Vision Systems PB - Springer Verlag CY - Sydney, Australia N1 - UT: 000287941400037ScopusID: 78650892305doi: 10.1007/978-3-642-17688-3_37 ER -