%0 Book Section %B Combinatorial Image Analysis %D 2014 %T Equivalent 2D sequential and parallel thinning %A Kálmán Palágyi %E Reneta P Barneva %E Valentin E Brimkov %E Josef Šlapal %B Combinatorial Image Analysis %I Springer %C Brno, Czech Republic %P 91 - 100 %8 May 2014 %G eng %9 Conference paper %0 Book Section %B Combinatorial Image Analysis %D 2014 %T Sufficient conditions for general 2D operators to preserve topology %A Péter Kardos %A Kálmán Palágyi %E Reneta P Barneva %E Valentin E Brimkov %E Josef Šlapal %X

An important requirement for various applications of binary image processing is to preserve topology. This issue has been earlier studied for two special types of image operators, namely, reductions and additions, and there have been some sufficient conditions proposed for them. In this paper, as an extension of those earlier results, we give novel sufficient criteria for general operators working on 2D pictures.

 

%B Combinatorial Image Analysis %S Lecture Notes in Computer Science %I Springer %C May 2014, Brno, Czech Republic %V 8466 %P 101 - 112 %8 2014 %@ 978-3-319-07147-3 %G eng %U http://dx.doi.org/10.1007/978-3-319-07148-0_10 %9 Conference paper %! Conference Paper %R 10.1007/978-3-319-07148-0_10 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 %D 2013 %T Bináris képek rekonstrukciója két vetületből és morfológiai vázból %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 %I NJSZT-KÉPAF %C Veszprém %P 182 - 193 %8 Jan 2013 %G eng %9 Conference paper %0 Journal Article %J ACTA CYBERNETICA-SZEGED %D 2013 %T Conference of PhD Students in Computer Science %A Kálmán Palágyi %B ACTA CYBERNETICA-SZEGED %V 21 %P 1 - 3 %8 2013 %@ 0324-721X %G eng %N 1 %9 Journal article %! ACTA CYBERN-SZEGED %0 Book Section %B Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications %D 2013 %T Deletion Rules for Equivalent Sequential and Parallel Reductions %A Kálmán Palágyi %E Jose Ruiz-Shulcloper %E Gabriella Sanniti di Baja %X

A reduction operator transforms a binary picture only by changing some black points to white ones, which is referred to as deletion. Sequential reductions may delete just one point at a time, while parallel reductions can alter a set of points simultaneously. Two reductions are called equivalent if they produce the same result for each input picture. This work lays a bridge between the parallel and the sequential strategies. A class of deletion rules are proposed that provide 2D parallel reductions being equivalent to sequential reductions. Some new sufficient conditions for topology-preserving parallel reductions are also reported.

%B Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications %S Lecture Notes in Computer Science %I Springer %C Berlin; Heidelberg %P 17 - 24 %8 Nov 2013 %@ 978-3-642-41821-1 %G eng %U http://link.springer.com/chapter/10.1007%2F978-3-642-41822-8_3 %9 Conference paper %! Conference Paper %R 10.1007/978-3-642-41822-8_3 %0 Book Section %B Advances in Visual Computing %D 2013 %T Parallel 3D 12-Subiteration Thinning Algorithms Based on Isthmuses %A Kálmán Palágyi %E George Bebis %X

Thinning is an iterative object reduction to obtain skeleton-like shape features of volumetric binary objects. Conventional thinning algorithms preserve endpoints to provide important geometric information relative to the object to be represented. An alternative strategy is also proposed that accumulates isthmuses (i.e., generalization of curve and surface interior points as skeletal elements). This paper presents two parallel isthmus-based 3D thinning algorithms that are capable of producing centerlines and medial surfaces. The strategy which is used is called subiteration-based or directional: each iteration step is composed of 12 subiterations each of which are executed in parallel. The proposed algorithms make efficient implementation possible and their topological correctness is guaranteed.

 

%B Advances in Visual Computing %S Lecture Notes in Computer Science %I Springer Verlag %C Heidelberg; New York %P 87 - 98 %8 Jul 2013 %G eng %9 Conference paper %R 10.1007/978-3-642-41914-0_10 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 %D 2013 %T Parallel Thinning Based on Isthmuses %A Gábor Németh %A Kálmán Palágyi %E László Czúni %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 %I NJSZT-KÉPAF %C Veszprém %P 512 - 525 %8 Jan 2013 %G eng %9 Conference paper %0 Book Section %B International Conference on Cognitive Infocommunications (CogInfoCom) %D 2013 %T Parallel Thinning on the Triangular Grid %A Péter Kardos %A Kálmán Palágyi %E Péter Baranyi %X

One of the fundamental issues of human and computational cognitive psychology is pattern or shape recognition. Various applications in image processing and computer vision rely on skeleton-like shape features A possible technique for extracting these feautures is thinning. Although the majority of 2D thinning algorithms work on digital pictures sampled onthe conventional square grid, the role of some non-conventional grids, like the hexagonal and triangular grid, are of increasing importance as well. In this paper we propose numerous topolgy preserving parallel thinning algorithms that work on the triangular grid.

%B International Conference on Cognitive Infocommunications (CogInfoCom) %I IEEE %C Budapest %P 277 - 282 %8 Dec 2013 %@ 978-1-4799-1543-9 %G eng %9 Conference paper %M 14046653 %R 10.1109/CogInfoCom.2013.6719256 %0 Book Section %B Proceedings of the IASTED International Conference on Computer Graphics and Imaging (CGIM) %D 2013 %T Sufficient Conditions for Topology Preserving Additions and General Operators %A Péter Kardos %A Kálmán Palágyi %E L Linsen %X

Topology preservation is a crucial issue of digital topology. Various applications of binary image processing rest on topology preserving operators. Earlier studies in this topic mainly concerned with reductions (i.e., operators that only delete some object points from binary images), as they form the basis for thinning algorithms. However, additions (i.e., operators that never change object points) also play important role for the purpose of generating discrete Voronoi diagrams or skeletons by influence zones (SKIZ). Furthermore, the use of general operators that may both add and delete some points to and from objects in pictures are suitable for contour smoothing. Therefore, in this paper we present some new sufficient conditions for topology preserving reductions, additions, and general operators. Two additions for 2D and 3D contour smoothing are also reported.

 

%B Proceedings of the IASTED International Conference on Computer Graphics and Imaging (CGIM) %I IASTED - Acta Press %C Calgary %P 107 - 114 %8 Feb 2013 %G eng %9 Conference paper %R 10.2316/P.2013.797-040 %0 Book Section %B Proceedings of International Symposium on Image and Signal Processing and Analysis (ISPA) %D 2013 %T On Topology Preservation in Triangular, Square, and Hexagonal Grids %A Péter Kardos %A Kálmán Palágyi %E Giovanni Ramponi %E Sven Lončarić %E Alberto Carini %E Karen Egiazarian %X

There are three possible partitionings of the continuous plane into regular polygons that leads to triangular, square, and hexagonal grids. The topology of the square grid is fairly well-understood, but it cannot be said of the remaining two regular sampling schemes. This paper presents a general characterization of simple pixels and some simplified sufficient conditions for topology-preserving operators in all the three types of regular grids.

%B Proceedings of International Symposium on Image and Signal Processing and Analysis (ISPA) %I IEEE %C Trieste %P 782 - 787 %8 Sep 2013 %G eng %9 Conference paper %M 14027933 %R 10.1109/ISPA.2013.6703844 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 %D 2013 %T Topology preserving parallel thinning on hexagonal grids %A Péter Kardos %A Kálmán Palágyi %E László Czúni %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 %I NJSZT-KÉPAF %C Veszprém %P 250 - 264 %8 Jan 2013 %G eng %9 Conference paper %0 Journal Article %J INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS %D 2013 %T Topology-preserving hexagonal thinning %A Péter Kardos %A Kálmán Palágyi %X

Thinning is a well-known technique for producing skeleton-like shape features from digital binary objects in a topology-preserving way. Most of the existing thinning algorithms work on input images that are sampled on orthogonal grids; however, it is also possible to perform thinning on hexagonal grids (or triangular lattices). In this paper, we point out to the main similarities and differences between the topological properties of these two types of sampling schemes. We give various characterizations of simple points and present some new sufficient conditions for topology-preserving reductions working on hexagonal grids.

%B INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS %I Taylor & Francis %V 90 %P 1607 - 1617 %8 2013 %@ 0020-7160 %G eng %U http://www.tandfonline.com/doi/abs/10.1080/00207160.2012.724198#preview %N 8 %9 Journal article %! INT J COMPUT MATH %R 10.1080/00207160.2012.724198 %0 Book Section %B Advanced Concepts for Intelligent Vision Systems (ACIVS) %D 2012 %T 3D Parallel Thinning Algorithms Based on Isthmuses %A Gábor Németh %A Kálmán Palágyi %E Jacques Blanc-Talon %E Wilfried Philips %E Dan Popescu %E Paul Scheunders %E Pavel Zemčík %X

Thinning is a widely used technique to obtain skeleton-like shape features (i.e., centerlines and medial surfaces) from digital binary objects. Conventional thinning algorithms preserve endpoints to provide important geometric information relative to the object to be represented. An alternative strategy is also proposed that preserves isthmuses (i.e., generalization of curve/surface interior points). In this paper we present ten 3D parallel isthmus-based thinning algorithm variants that are derived from some sufficient conditions for topology preserving reductions.

%B Advanced Concepts for Intelligent Vision Systems (ACIVS) %S Lecture Notes in Computer Science %I Springer Verlag %C Brno, Czech Republic %V 7517 %P 325 - 335 %8 Sep 2012 %G eng %U http://dx.doi.org/10.1007/978-3-642-33140-4_29 %9 Conference Paper %! Conference Paper %R 10.1007/978-3-642-33140-4_29 %0 Book Section %B Combinatorial Image Analysis %D 2012 %T Binary image reconstruction from two projections and skeletal information %A Norbert Hantos %A Péter Balázs %A Kálmán Palágyi %E Reneta P Barneva %E Valentin E Brimkov %E Jake K Aggarwal %X

In binary tomography, the goal is to reconstruct binary images from a small set of their projections. However, especially when only two projections are used, the task can be extremely underdetermined. In this paper, we show how to reduce ambiguity by using the morphological skeleton of the image as a priori. Three different variants of our method based on Simulated Annealing are tested using artificial binary images, and compared by reconstruction time and error. © 2012 Springer-Verlag.

%B Combinatorial Image Analysis %S Lecture Notes in Computer Science %I Springer Verlag %C Berlin; Heidelberg; New York; London; Paris; Tokyo %P 263 - 273 %8 Nov 2012 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-642-34732-0_20 %0 Conference Paper %B Conference of PhD Students in Computer Science %D 2012 %T Binary tomography using two projections and morphological skeleton %B Conference of PhD Students in Computer Science %I Univ Szeged Institute of Informatics %C Szeged %V Volume of Extended Abstracts %P 20 %8 June 2012 %G eng %0 Book Section %B Computational Modelling of Objects Represented in Images: Fundamentals, Methods and Applications III %D 2012 %T Hexagonal parallel thinning algorithms based on sufficient conditions for topology preservation %A Péter Kardos %A Kálmán Palágyi %E Paolo Di Giamberardino %E Daniela Iacoviello %E Renato M Natal Jorge %E Joao Manuel R S Taveres %X

Thinning is a well-known technique for producing skeleton-like shape features from digital
binary objects in a topology preserving way. Most of the existing thinning algorithms presuppose that the input
images are sampled on orthogonal grids.This paper presents new sufficient conditions for topology preserving
reductions working on hexagonal grids (or triangular lattices) and eight new 2D hexagonal parallel thinning
algorithms that are based on our conditions.The proposed algorithms are capable of producing both medial lines
and topological kernels as well.

%B Computational Modelling of Objects Represented in Images: Fundamentals, Methods and Applications III %I CRC Press - Taylor and Frances Group %C London %P 63 - 68 %8 2012 %@ 978-0-415-62134-2 %G eng %9 Conference paper %R 10.1201/b12753-12 %0 Conference Paper %B IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SSPRA) %D 2012 %T Isthmus-based Order-Independent Sequential Thinning %A Péter Kardos %A Kálmán Palágyi %E M Petrou %E A D Sappa %E A G Triantafyllidis %X

Thinning as a layer-by-layer reduction is a frequently used technique for skeletonization. Sequential thinning algorithms usually suffer from the drawback of being order-dependent, i.e., their results depend on the visiting order of object points. Earlier order-independent sequential methods are based on the conventional thinning schemes that preserve endpoints to provide relevant geometric information of objects. These algorithms can generate centerlines in 2D and medial surfaces in 3D. This paper presents an alternative strategy for order-independent thinning which follows an approach, proposed by Bertrand and Couprie, which accumulates so-called isthmus points. The main advantage of this order-independent strategy over the earlier ones is that it makes also possible to produce centerlines of 3D objects.

%B IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SSPRA) %I IASTED ACTA Press %C Crete, Greek %P 28 - 34 %8 June 2012 %G eng %U http://www.actapress.com/Content_of_Proceeding.aspx?proceedingID=736 %9 Conference paper %R 10.2316/P.2012.778-025 %0 Conference Paper %B IEEE International Conference on Cognitive Infocommunications (CogInfoCom) %D 2012 %T On Order–Independent Sequential Thinning %A Péter Kardos %A Kálmán Palágyi %E IEEE %X

The visual world composed by the human and computational cognitive systems strongly relies on shapes of objects. Skeleton is a widely applied shape feature that plays an important role in many fields of image processing, pattern recognition, and computer vision. Thinning is a frequently used, iterative object reduction strategy for skeletonization. Sequential thinning algorithms, which are based on contour tracking, delete just one border point at a time. Most of them have the disadvantage of order-dependence, i.e., for dissimilar visiting orders of object points, they may generate different skeletons. In this work, we give a survey of our results on order-independent thinning: we introduce some sequential algorithms that produce identical skeletons for any visiting orders, and we also present some sufficient conditions for the order-independence of templatebased sequential algorithms.

%B IEEE International Conference on Cognitive Infocommunications (CogInfoCom) %I IEEE %C Kosice, Slovakia %P 149 - 154 %8 2012 %@ 978-1-4673-5187-4 %G eng %U http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6413305 %9 Conference paper %R 10.1109/CogInfoCom.2012.6421971 %0 Conference Paper %B Veszprém Optimization Conference: Advanced Algorithms (VOCAL) %D 2012 %T Solving binary tomography from morphological skeleton via optimization %A Norbert Hantos %A Péter Balázs %A Kálmán Palágyi %B Veszprém Optimization Conference: Advanced Algorithms (VOCAL) %I University of Pannonia %C Veszprém %P 42 %8 Dec 2012 %G eng %9 Conference paper %0 Book Section %B Combinatorial Image Analysis (IWCIA) %D 2012 %T On topology preservation for triangular thinning algorithms %A Péter Kardos %A Kálmán Palágyi %E Reneta P Barneva %E Valentin E Brimkov %E Jake K Aggarwal %X

Thinning is a frequently used strategy to produce skeleton-like shape features of binary objects. One of the main problems of parallel thinning is to ensure topology preservation. Solutions to this problem have been already given for the case of orthogonal and hexagonal grids. This work introduces some characterizations of simple pixels and some sufficient conditions for parallel thinning algorithms working on triangular grids (or hexagonal lattices) to preserve topology.

%B Combinatorial Image Analysis (IWCIA) %S Lecture Notes in Computer Science %I Springer Verlag %C Austin, TX, USA %P 128 - 142 %8 Nov 2012 %@ 978-3-642-34731-3 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-642-34732-0_10 %0 Book Section %B Digital Geometry Algorithms %D 2012 %T Topology Preserving Parallel 3D Thinning Algorithms %A Kálmán Palágyi %A Gábor Németh %A Péter Kardos %E Valentin E Brimkov %E Reneta P Barneva %X

A widely used technique to obtain skeletons of binary objects is thinning, which is an iterative layer-by-layer erosion in a topology preserving way. Thinning in 3D is capable of extracting various skeleton-like shape descriptors (i.e., centerlines, medial surfaces, and topological kernels). This chapter describes a family of new parallel 3D thinning algorithms for (26, 6) binary pictures. The reported algorithms are derived from some sufficient conditions for topology preserving parallel reduction operations, hence their topological correctness is guaranteed.

%B Digital Geometry Algorithms %S Lecture Notes in Computational Vision and Biomechanics %I Springer-Verlag %P 165 - 188 %8 2012 %@ 978-94-007-4173-7 %G eng %9 Book chapter %& 6 %R 10.1007/978-94-007-4174-4_6 %0 Conference Paper %B Proceedings of the International Symposium on Image and Signal Processing and Analysis (ISPA) %D 2011 %T 2D Parallel Thinning Algorithms Based on Isthmus-Preservation %A Gábor Németh %A Kálmán Palágyi %E Sven Lončarić %E Giovanni Ramponi %E D. Sersic %X

Skeletons are widely used shape descriptors which summarize the general form of binary objects. A technique to obtain skeletons is the thinning, that is an iterative layer-by-layer erosion in a topology-preserving way. Conventional thinning algorithms preserve line endpoints to provide important geometric information relative to the object to be represented. Bertrand and Couprie proposed an alternative strategy by accumulating isthmus points that are line interior points. In this paper we present six new 2D parallel thinning algorithms that are derived from some sufficient conditions for topology preserving reductions and based on isthmus-preservation.

%B Proceedings of the International Symposium on Image and Signal Processing and Analysis (ISPA) %I IEEE %C Dubrovnik, Croatia %P 585 - 590 %8 Sep 2011 %@ 978-1-4577-0841-1 %G eng %9 Conference paper %M 12307467 %0 Journal Article %J ACTA CYBERNETICA-SZEGED %D 2011 %T 2D parallel thinning and shrinking based on sufficient conditions for topology preservation %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %X

Thinning and shrinking algorithms, respectively, are capable of extracting medial lines and topological kernels from digital binary objects in a topology preserving way. These topological algorithms are composed of reduction operations: object points that satisfy some topological and geometrical constraints are removed until stability is reached. In this work we present some new sufficient conditions for topology preserving parallel reductions and fiftyfour new 2D parallel thinning and shrinking algorithms that are based on our conditions. The proposed thinning algorithms use five characterizations of endpoints.

%B ACTA CYBERNETICA-SZEGED %I University of Szeged, Institute of Informatics %C Szeged %V 20 %P 125 - 144 %8 2011 %@ 0324-721X %G eng %N 1 %9 Journal article %! ACTA CYBERN-SZEGED %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T 3D objektumok lineáris deformációinak becslése %A Attila Tanacs %A Joakim Lindblad %A Nataša Sladoje %A Zoltan Kato %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 471 - 480 %8 Jan 2011 %G eng %9 Conference paper %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T Affin Puzzle: Deformált objektumdarabok helyreállítása megfeleltetések nélkül %A Csaba Domokos %A Zoltan Kato %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 206 - 220 %8 Jan 2011 %G eng %U http://www.inf.u-szeged.hu/kepaf2011/pdfs/S05_03.pdf %9 Conference paper %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T Bináris tomográfiai rekonstrukció objektum alapú evolúciós algoritmussal %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 117 - 127 %8 Jan 2011 %G eng %9 Conference paper %0 Journal Article %J ACTA CYBERNETICA-SZEGED %D 2011 %T Conference of PhD Students in Computer Science %A Kálmán Palágyi %B ACTA CYBERNETICA-SZEGED %V 20 %P 3 %8 2011 %@ 0324-721X %G eng %N 1 %9 Journal article %! ACTA CYBERN-SZEGED %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T Élősejt szegmentálása gráfvágás segítségével fluoreszcenciás mikroszkóp képeken %A Milan Lesko %A Zoltan Kato %A Antal Nagy %A Imre Gombos %A Zsolt Török %A László Vígh %A László Vígh %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 319 - 328 %8 Jan 2011 %G eng %U http://www.inf.u-szeged.hu/kepaf2011/pdfs/S08_02.pdf %9 Conference paper %0 Book Section %B Combinatorial Image Analysis (IWCIA) %D 2011 %T A family of topology-preserving 3d parallel 6-subiteration thinning algorithms %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %E Jake K Aggarwal %E Reneta P Barneva %E Valentin E Brimkov %E Kostadin N Koroutchev %E Elka R Korutcheva %X

Thinning is an iterative layer-by-layer erosion until only the skeleton-like shape features of the objects are left. This paper presents a family of new 3D parallel thinning algorithms that are based on our new sufficient conditions for 3D parallel reduction operators to preserve topology. The strategy which is used is called subiteration-based: each iteration step is composed of six parallel reduction operators according to the six main directions in 3D. The major contributions of this paper are: 1) Some new sufficient conditions for topology preserving parallel reductions are introduced. 2) A new 6-subiteration thinning scheme is proposed. Its topological correctness is guaranteed, since its deletion rules are derived from our sufficient conditions for topology preservation. 3) The proposed thinning scheme with different characterizations of endpoints yields various new algorithms for extracting centerlines and medial surfaces from 3D binary pictures. © 2011 Springer-Verlag Berlin Heidelberg.

%B Combinatorial Image Analysis (IWCIA) %S Lecture Notes in Computer Science %I Springer Verlag %C Madrid, Spain %P 17 - 30 %8 May 2011 %@ 978-3-642-21072-3 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-642-21073-0_5 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T Iterációnkénti simítással kombinált vékonyítás %A Péter Kardos %A Gábor Németh %A Kálmán Palágyi %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 174 - 189 %8 Jan 2011 %G eng %U http://www.inf.u-szeged.hu/kepaf2011/pdfs/S05_01.pdf %9 Conference paper %0 Book %D 2011 %T Képfeldolgozás haladóknak %A Kálmán Palágyi %I Typotex %C Budapest %8 2011 %G eng %9 Book %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T Mediánszűrés alkalmazása algebrai rekonstrukciós módszerekben %A Norbert Hantos %A Péter Balázs %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 106 - 116 %8 Jan 2011 %G eng %9 Conference paper %0 Conference Paper %B Signal and Image Processing and Applications (SIPA) %D 2011 %T Order-independent sequential thinning in arbitrary dimensions %A Péter Kardos %A Kálmán Palágyi %E Ioannis Andreadis %E M Zervakis %X

Skeletons are region based shape descriptors that play important role in shape representation. This paper introduces a novel sequential thinning approach for n-dimensional binary objects (n =1,2,3, ...). Its main strength lies in its order--independency, i.e., it can produce the same skeletons for any visiting orders of border points. Furthermore, this is the first scheme in this field that is also applicable for higher dimensions.

%B Signal and Image Processing and Applications (SIPA) %I IASTED - Acta Press %C Crete, Greek %P 129 - 134 %8 June 2011 %G eng %9 Conference paper %R 10.2316/P.2011.738-021 %0 Journal Article %J GRAPHICAL MODELS %D 2011 %T Thinning combined with iteration-by-iteration smoothing for 3D binary images %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %X

In this work we present a new thinning scheme for reducing the noise sensitivity of 3D thinning algorithms. It uses iteration-by-iteration smoothing that removes some border points that are considered as extremities. The proposed smoothing algorithm is composed of two parallel topology preserving reduction operators. An efficient implementation of our algorithm is sketched and its topological correctness for (26, 6) pictures is proved. © 2011 Elsevier Inc. All rights reserved.

%B GRAPHICAL MODELS %V 73 %P 335 - 345 %8 Nov 2011 %@ 1524-0703 %G eng %N 6 %9 Journal article %! GRAPH MODELS %R 10.1016/j.gmod.2011.02.001 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T A topológia-megőrzés elegendő feltételein alapuló 3D párhuzamos vékonyító algoritmusok %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 190 - 205 %8 Jan 2011 %G hun %U http://www.inf.u-szeged.hu/kepaf2011/pdfs/S05_02.pdf %9 Conference paper %0 Book Section %B Combinatorial Image Analysis (IWCIA) %D 2011 %T On topology preservation for hexagonal parallel thinning algorithms %A Péter Kardos %A Kálmán Palágyi %E Jake K Aggarwal %E Reneta P Barneva %E Valentin E Brimkov %E Kostadin N Koroutchev %E Elka R Korutcheva %X

Topology preservation is the key concept in parallel thinning algorithms on any sampling schemes. This paper establishes some sufficient conditions for parallel thinning algorithms working on hexagonal grids (or triangular lattices) to preserve topology. By these results, various thinning (and shrinking to a residue) algorithms can be verified. To illustrate the usefulness of our sufficient conditions, we propose a new parallel thinning algorithm and prove its topological correctness. © 2011 Springer-Verlag Berlin Heidelberg.

%B Combinatorial Image Analysis (IWCIA) %S Lecture Notes in Computer Science %I Springer Verlag %C Madrid, Spain %P 31 - 42 %8 May 2011 %@ 978-3-642-21072-3 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-642-21073-0_6 %0 Journal Article %J INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY %D 2011 %T Topology Preserving Parallel Thinning Algorithms %A Gábor Németh %A Kálmán Palágyi %X

Thinning is an iterative object reduction technique for extracting medial curves from binary objects. During a thinning process, some border points that satisfy certain topological and geometric constraints are deleted in iteration steps. Parallel thinning algorithms are composed of parallel reduction operators that delete a set of object points simultaneously. This article presents 21 parallel thinning algorithms for (8,4) binary pictures that are derived from the sufficient conditions for topology preservation accommodated to the three parallel thinning approaches. © 2011 Wiley Periodicals, Inc.

%B INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY %I Wiley Periodicals, Inc. %V 21 %P 37 - 44 %8 Feb 2011 %@ 0899-9457 %G eng %N 1 %9 Journal article %! INT J IMAG SYST TECH %R 10.1002/ima.20272 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %D 2011 %T Vetületi irányfüggőség a bináris tomográfiában %A László Gábor Varga %A Péter Balázs %A Antal Nagy %E Zoltan Kato %E Kálmán Palágyi %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 %I NJSZT %C Szeged %P 92 - 105 %8 Jan 2011 %G hun %9 Conference paper %0 Journal Article %J ALKALMAZOTT MATEMATIKAI LAPOK %D 2010 %T Bejárásfüggetlen szekvenciális vékonyítás %A Péter Kardos %A Gábor Németh %A Kálmán Palágyi %B ALKALMAZOTT MATEMATIKAI LAPOK %V 27 %P 17 - 40 %8 2010 %@ 0133-3399 %G eng %N 1 %9 Journal article %! ALKALMAZOTT MATEMATIKAI LAPOK %0 Book Section %B Progress in Combinatorial Image Analysis %D 2010 %T Parallel Thinning Algorithms Based on Ronse's Sufficient Conditions for Topology Preservation %A Gábor Németh %A Kálmán Palágyi %E Petra Wiederhold %E Reneta P Barneva %B Progress in Combinatorial Image Analysis %I Scientific Research Publishing Inc. %C Singapore %P 183 - 194 %8 May 2010 %G eng %U http://rpsonline.com.sg/rpsweb/iwcia09.html %9 Book chapter %0 Conference Paper %B Proceedings of the International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA) %D 2010 %T Topology preserving 2-subfield 3D thinning algorithms %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %E B Zagar %E A Kuijper %E H Sahbi %X

This paper presents a new family of 3D thinning algorithms for extracting skeleton-like shape features (i.e, centerline, medial surface, and topological kernel) from volumetric images. A 2-subfield strategy is applied: all points in a 3D picture are partitioned into two subsets which are alternatively activated. At each iteration, a parallel operator is applied for deleting some border points in the active subfield. The proposed algorithms are derived from Ma's sufficient conditions for topology preservation, and they use various endpoint characterizations.

%B Proceedings of the International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA) %I IASTED ACTA Press %C Innsbruck, Austria %P 310 - 316 %8 Feb 2010 %G eng %9 Conference paper %0 Book Section %B Proceedings of the International Conference on Image Analysis and Recognition (ICIAR) %D 2010 %T Topology Preserving 3D Thinning Algorithms using Four and Eight Subfields %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %E Aurélio Campilho %E Mohamed Kamel %X

Thinning is a frequently applied technique for extracting skeleton-like shape features (i.e., centerline, medial surface, and topological kernel) from volumetric binary images. Subfield-based thinning algorithms partition the image into some subsets which are alternatively activated, and some points in the active subfield are deleted. This paper presents a set of new 3D parallel subfield-based thinning algorithms that use four and eight subfields. The three major contributions of this paper are: 1) The deletion rules of the presented algorithms are derived from some sufficient conditions for topology preservation. 2) A novel thinning scheme is proposed that uses iteration-level endpoint checking. 3) Various characterizations of endpoints yield different algorithms. © 2010 Springer-Verlag.

%B Proceedings of the International Conference on Image Analysis and Recognition (ICIAR) %S Lecture Notes in Computer Science %I Springer Verlag %C Póvoa de Varzim, Portugal %V 6111 %P 316 - 325 %8 June 2010 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-642-13772-3_32 %0 Book Section %B Proceedings of the Computational Modeling of Objects Represented in Images (CMORI) %D 2010 %T Topology Preserving Parallel Smoothing for 3D Binary Images %A Gábor Németh %A Péter Kardos %A Kálmán Palágyi %E Reneta P Barneva %E Valentin E Brimkov %E Herbert A Hauptman %E Renato M Natal Jorge %E João Manuel R S Tavares %X

This paper presents a new algorithm for smoothing 3D binary images in a topology preserving way. Our algorithm is a reduction operator: some border points that are considered as extremities are removed. The proposed method is composed of two parallel reduction operators. We are to apply our smoothing algorithm as an iteration-by-iteration pruning for reducing the noise sensitivity of 3D parallel surface-thinning algorithms. An efficient implementation of our algorithm is sketched and its topological correctness for (26,6) pictures is proved. © 2010 Springer-Verlag.

%B Proceedings of the Computational Modeling of Objects Represented in Images (CMORI) %I Springer Verlag %C Buffalo, USA %V 6026 %P 287 - 298 %8 May 2010 %G eng %9 Conference paper %R 10.1007/978-3-642-12712-0_26 %0 Journal Article %J ACTA CYBERNETICA-SZEGED %D 2009 %T Conference of PhD Students in Computer Science %A Kálmán Palágyi %B ACTA CYBERNETICA-SZEGED %V 19 %P 3 %8 2009/// %@ 0324-721X %G eng %N 1 %! ACTA CYBERN-SZEGED %0 Book Section %B Proceedings of Discrete Geometry for Computer Imagery (DGCI) %D 2009 %T Fully Parallel 3D Thinning Algorithms based on Sufficient Conditions for Topology Preservation %A Kálmán Palágyi %A Gábor Németh %E Srecko Brlek %E Christophe Reutenauer %E Xavier Provençal %X

This paper presents a family of parallel thinning algorithms for extracting medial surfaces from 3D binary pictures. The proposed algorithms are based on sufficient conditions for 3D parallel reduction operators to preserve topology for (26,6) pictures. Hence it is self-evident that our algorithms are topology preserving. Their efficient implementation on conventional sequential computers is also presented. © 2009 Springer Berlin Heidelberg.

%B Proceedings of Discrete Geometry for Computer Imagery (DGCI) %I Springer Verlag %C Montreal, Quebec, Canada %P 481 - 492 %8 Sep 2009 %@ 978-3-642-04396-3 %G eng %9 Conference paper %R 10.1007/978-3-642-04397-0_41 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 %D 2009 %T Kritikus párokat vizsgáló bejárásfüggetlen szekvenciális vékonyító algoritmus %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 %I Akaprint %C Budapest %P 1 - 8 %8 Jan 2009 %G hun %9 Conference paper %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 %D 2009 %T A morfológiai váz általánosítása szomszédsági szekvenciákkal %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 %I Akaprint %C Budapest %P 1 - 10 %8 Jan 2009 %G eng %9 Conference paper %0 Book Section %B Proceedings of the International Workshop on Combinatorial Image Analysis (IWCIA) %D 2009 %T An order-independent sequential thinning algorithm %A Péter Kardos %A Gábor Németh %A Kálmán Palágyi %E Petra Wiederhold %E Reneta P Barneva %X

Thinning is a widely used approach for skeletonization. Sequential thinning algorithms use contour tracking: they scan border points and remove the actual one if it is not designated a skeletal point. They may produce various skeletons for different visiting orders. In this paper, we present a new 2-dimensional sequential thinning algorithm, which produces the same result for arbitrary visiting orders and it is capable of extracting maximally thinned skeletons. © Springer-Verlag Berlin Heidelberg 2009.

%B Proceedings of the International Workshop on Combinatorial Image Analysis (IWCIA) %I Springer Verlag %C Playa del Carmen, Mexico %P 162 - 175 %8 Nov 2009 %@ 978-3-642-10208-0 %G eng %U http://link.springer.com/chapter/10.1007/978-3-642-10210-3_13 %9 Conference paper %R 10.1007/978-3-642-10210-3_13 %0 Journal Article %J DISCRETE APPLIED MATHEMATICS %D 2009 %T Preface to the Special Issue %B DISCRETE APPLIED MATHEMATICS %V 157 %P 437 %8 2009/// %@ 0166-218X %G eng %N 3 %! DISCRETE APPL MATH %0 Journal Article %J THEORETICAL COMPUTER SCIENCE %D 2008 %T A 3D fully parallel surface-thinning algorithm %A Kálmán Palágyi %X

The thinning is an iterative layer by layer erosion until only the "skeletons" of the objects are left. This paper presents a thinning algorithm for extracting medial surfaces from 3D binary pictures. The strategy which is used is called fully parallel, which means that the same parallel operator is applied at each iteration. An efficient implementation of the proposed algorithm on conventional sequential computers is given and the topological correctness for (26, 6) binary pictures is proved. © 2008 Elsevier B.V. All rights reserved.

%B THEORETICAL COMPUTER SCIENCE %I Elsevier %C AHUJA N, 1997, IEEE T PATTERN ANAL, V19, P169ARCELLI C, 2006, LECT NOTES COMPUT SC, V4245, P555BERTRAND G, 1994, P SPIE C VISION GEOM, V2356, P113BERTRAND G, 1995, CR ACAD SCI I-MATH, V321, P1077BERTRAND G, 1995, P 5 INT C DISCR GEOM, P233BERTRAND G, %V 406 %P 119 - 135 %8 Oct 2008 %@ 0304-3975 %G eng %N 1-2 %9 Journal article %! THEOR COMPUT SCI %R 10.1016/j.tcs.2008.06.041 %0 Conference Paper %B Conference of PhD Students in Computer Science. Volume of Extended Abstracts %D 2008 %T Determination of geometric features of binary images from their projections by using decision trees %A Mihály Gara %A Péter Balázs %E Kálmán Palágyi %E Balázs Bánhelyi %E Tamás Gergely %E István Matievics %B Conference of PhD Students in Computer Science. Volume of Extended Abstracts %I University of Szeged %C Szeged, Hungary %P 26 %8 July 2008 %G eng %9 Abstract %0 Book Section %B Informatika a felsőoktatásban 2008 %D 2008 %T A képfeldolgozás kutatása a Szegedi Tudományegyetemen %X A digitális képfeldolgozás kutatásának a Szegedi TudományegyetemTermészettudományi és Informatikai Karán, az Informatikai Tanszékcsoport Képfeldolgozás és Számítógépes Grafika Tanszékén közel négy évtizedes hagyománya van. A Tanszék valamennyi munkatársa nemzetközileg elismert kutatómunkát folytat, melyet már több száz rangos publikáció fémjelez. Számos, a képfeldolgozás kutatásában vezető egyetemmel és kutatóintézettel építettünk ki szoros kapcsolatot és folytattunk eredményes kutatómunkát, aktív résztvevői vagyunk a hazai és a nemzetközi tudományos közéletnek. A legfontosabb, jelenleg is folyó kutatásaink: orvosi képek feldolgozása, diszkrét tomográfia, képszegmentálás, térinformatika, távérzékelés, képregisztráció, vázkijelölés, műtéti tervezés. %B Informatika a felsőoktatásban 2008 %I Debreceni Egyetem Informatikai Kar %C Debrecen %8 2008/// %G eng %U http://www.agr.unideb.hu/if2008/kiadvany/papers/E62.pdf %0 Book Section %B Computer Vision Systems %D 2008 %T Skeletonization based on metrical neighborhood sequences %A Attila Fazekas %A Kálmán Palágyi %A György Kovács %A Gábor Németh %E Antonios Gasteratos %E Markus Vincze %E John K Tsotsos %X

Skeleton is a shape descriptor which summarizes the general formof objects. It can be expressed in terms of the fundamental morphological operations. The limitation of that characterization is that its construction based on digital disks such that cannot provide good approximation to the Euclidean disks. In this paper we define a new type of skeleton based on neighborhood sequences that is much closer to the Euclidean skeleton. A novel method for quantitative comparison of skeletonization algorithms is also proposed. © 2008 Springer- Verlag Berlin Heidelberg.

%B Computer Vision Systems %I Springer Verlag %C Santorini, Greece %P 333 - 342 %8 May 2008 %@ 978-3-540-79546-9 %G eng %9 Conference paper %R 10.1007/978-3-540-79547-6_32 %0 Book Section %B Image Processing in Radiology %D 2008 %T Techniques of Virtual Dissection of the Colon Based on Spiral CT Data %A Erich Sorantin %A Emese Balogh %A Anna Vilanova Bartroli %A Kálmán Palágyi %A László Gábor Nyúl %A Franz Lindbichler %A Andrea Ruppert %E Emanuele Neri %E Davide Caramella %E Carlo Bartolozzi %X

Colorectal cancer represents the third most commonly diagnosedcancer and is the second leading cause of cancer deaths in the United States (Gazelle et al. 2000). In addition, colorectal cancer is responsible for about 11% of all new cancer cases per year (Gazelle et al. 2000). Five-year prognosis is about 90% for patients with localized disease compared to 60% if there is a regional spread and a drop to 10% in patients with distant metastasis (Gazelle et al. 2000). In the field of medicine there is a widely accepted opinion that most colorectal cancers arise from pre-existent adenomatous polyps (Johnson 2000). Therefore, different societies, such as the American Cancer Society, have proposed screening for colorectal cancer (Byers et al. 1997; Winawer et al. 1997). Today, different options exist for detection of colorectal cancer, including digital rectal examination, fecal occult blood testing, flexible and rigid sigmoidoscopy, barium enema and its variants, colonoscopy and recently computed tomography or magnetic resonance-based virtual colonography (Gazelle et al. 2000).

%B Image Processing in Radiology %I Springer-Verlag %C Berlin %P 257 - 268 %8 2008 %G eng %9 Book chapter %R 10.1007/978-3-540-49830-8_18 %0 Book Section %B Computer Analysis of Images and Patterns %D 2007 %T A 3-subiteration surface-thinning algorithm %A Kálmán Palágyi %E Walter G Kropatsch %E Martin Kampel %E Allan Hanbury %X

Thinning is an iterative layer by layer erosion for extractingskeleton. This paper presents an efficient parallel 3D thinning algorithm which produces medial surfaces. A three-subiteration strategy is proposed: the thinning operation is changed from iteration to iteration with a period of three according to the three deletion directions. © Springer-Verlag Berlin Heidelberg 2007.

%B Computer Analysis of Images and Patterns %S Lecture Notes in Computer Science %I Springer Verlag %C Vienna, Austria %P 628 - 635 %8 Aug 2007 %@ 978-3-540-74271-5 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-540-74272-2_78 %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 %D 2007 %T Alakreprezentáció szférikus harmonikus sorfejtéssel %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 %I Képfeldolgozók és Alakfelismerők Társasága %C Debrecen %P 275 - 282 %8 Jan 2007 %G eng %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 %D 2007 %T Efficient Implementation of 3D Thinning Algorithms %A Kálmán Palágyi %E Attila Fazekas %E András Hajdú %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 %I Képfeldolgozók és Alakfelismerők Társasága %C Debrecen %P 266 - 274 %8 Jan 2007 %G eng %0 Book Section %B Pattern Recognition %D 2007 %T A subiteration-based surface-thinning algorithm with a period of three %A Kálmán Palágyi %E Fred A Hamprecht %E Christoph Schnorr %E Bernd Jähne %X

Thinning on binary images is an iterative layer by layer erosionuntil only the "skeletons" of the objects are left. This paper presents an efficient parallel 3D surface-thinning algorithm. A three-subiteration strategy is proposed: the thinning operation is changed from iteration to iteration with a period of three according to the three deletion directions. © Springer-Verlag Berlin Heidelberg 2007.

%B Pattern Recognition %S Lecture Notes on Computer Science %I Springer Verlag %C Heidelberg, Germany %P 294 - 303 %8 Sep 2007 %@ 978-3-540-74933-2 %G eng %9 Conference paper %! LNCS %R 10.1007/978-3-540-74936-3_30 %0 Book Section %B Discrete Geometry for Computer Imagery %D 2006 %T A benchmark evaluation of large-scale optimization approaches to binary tomography %B Discrete Geometry for Computer Imagery %I Springer-Verlag %C Berlin; Heidelberg %P 146 - 156 %8 2006 %G eng %0 Conference Proceedings %B Discrete Geometry for Computer Imagery %D 2006 %T Discrete Geometry for Computer Imagery %X

This book constitutes the refereed proceedings of the 13th International Conference on Discrete Geometry for Computer Imagery, DGCI 2006, held in Szeged, Hungary in October 2006. The 28 revised full papers and 27 revised poster papers presented together with 2 invited papers were carefully reviewed and selected from 99 submissions. The papers are organized in topical sections on discrete geometry, discrete tomography, discrete topology, distance, image analysis, shape representation, segmentation, skeletonization, as well as surfaces and volumes.

%B Discrete Geometry for Computer Imagery %S Lecture Notes in Computer Science %I Springer-Verlag %V 4245 %P 688 %8 2006 %G eng %U http://www.springerlink.com/content/t38633812l42/ %! LNCS %R 10.1007/11907350 %0 Book Section %B Digital (r)evolution in radiology %D 2006 %T New advances for imaging laryngo / trachealstenosis by post processing of spiral-CT data %B Digital (r)evolution in radiology %I Springer-Verlag %C Wien; New York %P 297 - 308 %8 2006/// %G eng %0 Book Section %B Discrete Geometry for Computer Imagery %D 2006 %T The number of line-convex directed polyominoes having the same orthogonal projections %X

The number of line-convex directed polyominoes with givenhorizontal and vertical projections is studied. It is proven that diagonally convex directed polyominoes are uniquely determined by their orthogonal projections. The proof of this result is algorithmical. As a counterpart, we show that ambiguity can be exponential if antidiagonal convexity is assumed about the polyomino. Then, the results are generalised to polyominoes having convexity property along arbitrary lines. © Springer-Verlag Berlin Heidelberg 2006.

%B Discrete Geometry for Computer Imagery %I Springer-Verlag %C Berlin, Heidelberg %P 77 - 85 %8 2006/// %G eng %0 Journal Article %J COMPUTERS IN BIOLOGY AND MEDICINE %D 2006 %T Quantitative analysis of pulmonary airway tree structures %X A method for computationally efficient skeletonization of three-dimensional tubular structures is reported. The method is specifically targeting skeletonization of vascular and airway tree structures in medical images but it is general and applicable to many other skeletonization tasks. The developed approach builds on the following novel concepts and properties: fast curve-thinning algorithm to increase computational speed, endpoint re-checking to avoid generation of spurious side branches, depth-and-length sensitive pruning, and exact tree-branch partitioning allowing branch volume and surface measurements. The method was validated in computer and physical phantoms and in vivo CT scans of human lungs. The validation studies demonstrated sub-voxel accuracy of branch point positioning, insensitivity to changes of object orientation, and high reproducibility of derived quantitative indices of the tubular structures offering a significant improvement over previously reported methods (p ≪ 0.001). © 2005 Elsevier Ltd. All rights reserved. %B COMPUTERS IN BIOLOGY AND MEDICINE %C ANTIGA L, 2003, IEEE T MED IMAGING, V22, P674, DOI10.1109/TMI.2003.812261 AYLWARD SR, 2002, IEEE T MED IMAGING, V21, P61 BLAND JM, 1986, LANCET, V1, P307 BORGEFORS G, 1984, COMPUT VISION GRAPH, V27, P321 BOUIX S, 2003, IEEE C COMP VIS PATT, P449 CHEN ZK, %V 36 %P 974 - 996 %8 2006/// %@ 0010-4825 %G eng %N 9 %! COMPUT BIOL MED %0 Book Section %B Joint Hungarian-Austrian conference on image processing and pattern recognition. 5th conference of the Hungarian Association for Image Processing and Pattern Recognition (KÉPAF), 29th workshop of the Austrian Association for Pattern Reco %D 2005 %T A 2-Subfield 3D Thinning Algorithm for Extracting Medial Curves %B Joint Hungarian-Austrian conference on image processing and pattern recognition. 5th conference of the Hungarian Association for Image Processing and Pattern Recognition (KÉPAF), 29th workshop of the Austrian Association for Pattern Reco %I OCG %C Vienna %P 135 - 142 %8 2005/// %G eng %0 Journal Article %J IEEE TRANSACTIONS ON MEDICAL IMAGING %D 2005 %T Matching and anatomical labeling of human airway tree %X Matching of corresponding branchpoints between two human airway trees, as well as assigning anatomical names to the segments and branchpoints of the human airway tree, are of significant interest for clinical applications and physiological studies. In the past, these tasks were often performed manually due to the lack of automated algorithms that can tolerate false branches and anatomical variability typical for in vivo trees. In this paper, we present algorithms that perform both matching of branchpoints and anatomical labeling of in vivo trees without any human intervention and within a short computing time. No hand-pruning of false branches is required. The results from the automated methods show a high degree of accuracy when validated against reference data provided by human experts. 92.9% of the verifiable branchpoint matches found by the computer agree with experts' results. For anatomical labeling, 97.1 % of the automatically assigned segment labels were found to be correct. © 2005 IEEE. %B IEEE TRANSACTIONS ON MEDICAL IMAGING %C BALLARD DH, 1982, COMPUTER VISIONBOYDEN EA, 1955, SEGMENTAL ANATOMY LU CARRAGHAN R, 1990, OPER RES LETT, V9, P375 GAREY MR, 1979, COMPUTERS INTRACTABI KITAOKA H, 2002, P MICCAI 2002 TOKYO, P1 MORI K, 2000, IEEE T MED IMAGING, V19, P103 PALAGYI K, 2003, LE %V 24 %P 1540 - 1547 %8 2005/// %@ 0278-0062 %G eng %N 12 %! IEEE T MED IMAGING %0 Book Section %B Medical Imaging Systems Technology %D 2005 %T Techniques in 3D Assessment of Tracheal-Stenosis by the Mean of Spiral Computed Tomography (S-CT) and Their Applications %X Endotracheal intubation is the most common cause of Laryngo-Tracheal Stenoses (LTS), followed by trauma and prior airway surgery.1–3 In rare cases LTS may have resulted also from inhalation injuries, gastro-esophageal reflux disease, neoplasia and autoimmune diseases like Wegeners granulomatosis or relapsing polychondritis.1,4 In pediatric patients vascular compression of the trachea is a common cause of tracheal indentations.5 Clinical management of these conditions requires information on localization, grade, length and dynamics of the stenosis. Exact LTS information is necessary, since stenoses with a length less than 1.0 cm can be treated by an endoscopic surgery.6,7 Besides Fiberoptic Endoscopy (FE), which represents the gold standard for airway evaluation, imaging modalities like conventional radiography, fluoroscopy, tracheal tomograms, Magnetic Resonance Imaging (MRI) and above all Spiral Computed Tomography (S-CT) are an essential part of the clinical work.1,8 S-CT and the recent introduction of multislice imaging allows volumetric data acquisition of the Laryngo–Tracheal Tract (LTT) during a short time span. Decreased motion artifacts and increased spatial resolution form the basis for high quality post processing.9,10 The improved performance of today's workstations permits the use of sophisticated post processing algorithms even on standard hardware like personal computers. Thus real time 3D display and virtual endoscopic views (virtual endoscopy) are just one mouse click away. Other algorithms compute the medial axis of tubular structures like airways or vessels in 3D, which can be used for the calculation of 3D cross sectional profiles for better demonstration of caliber changes.11 Thus display of S-CT axial source images is moving rapidly to 3D display. Moreover, established network connections within and between institutions allows telemedical cooperation. Web technologies offer an easy to use way for information exchange. The objective of this paper is to present an overview on 3D display and quantification of LTS as well as to provide information how these results can be presented and shared with the referring physicians on the hospitals computer network. This article is structured in seven parts; namely: S-CT data acquisition for LTS imaging; selected 3D image post processing algorithms; 3D display; Virtual endoscopy; Objective LTS degree and length estimation using LTT 3D — cross-sectional profiles; Intranet applications; and a conclusion is drawn in the final section. %B Medical Imaging Systems Technology %I World Scientific %C Singapore %P 61 - 80 %8 2005/// %G eng %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 2004 %T Assessment of intrathoracic airway trees: Methods and in vivo validation %B LECTURE NOTES IN COMPUTER SCIENCE %C BLAND JM, 1986, LANCET, V1, P307CHEN ZK, 2003, COMPUT MED IMAG GRAP, V27, P469, DOI 10.1016/S0895-6111(03)00039-9 GERIG G, 1993, LECT NOTES COMPUTER, V687, P94 KITAOKA H, 1999, J APPL PHYSIOL, V87, P2207 KONG TY, 1989, COMPUT VISION GRAPH, V48, P357 MADDA %V 3117 %P 341 - 352 %8 2004/// %@ 0302-9743 %G eng %! LECT NOTES COMPUT SCI %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 %D 2004 %T Légutak vizsgálata 3D CT-képeken %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 %I Neumann János Számítógép-tudományi Társaság %C Miskolc %P 232 - 236 %8 Jan 2004 %G eng %0 Book Section %B Medical Imaging 2004: Image Processing %D 2004 %T Liver segment approximation in CT data for surgical resection planning %X Surgical planning of liver tumor resections requires detailed three-dimensional (3D) understanding of the complex arrangement of vasculature, liver segments and tumors. Knowledge about location and sizes of liver segments is important for choosing an optimal surgical resection approach and predicting postoperative residual liver capacity. The aim of this work is to facilitate such surgical planning process by developing a robust method for portal vein tree segmentation. The work also investigates the impact of vessel segmentation on the approximation of liver segment volumes. For segment approximation, smaller portal vein branches are of importance. Small branches, however, are difficult to segment due to noise and partial volume effects. Our vessel segmentation is based on the original gray-values and on the result of a vessel enhancement filter. Validation of the developed portal vein segmentation method in computer generated phantoms shows that, compared to a conventional approach, more vessel branches can be segmented. Experiments with in vivo acquired liver CT data sets confirmed this result. The outcome of a Nearest Neighbor liver segment approximation method applied to phantom data demonstrates, that the proposed vessel segmentation approach translates into a more accurate segment partitioning. %B Medical Imaging 2004: Image Processing %I SPIE %C Bellingham; WashingtonScheele, J., Anatomical and atypical liver resection (2001) Chirurg, 72 (2), pp. 113-124;Couinaud, C., (1957) Le Foie - Etudes Anatomiques et Chirurgicales, , Masson, Paris; Strunk, H., Stuckmann, G., Textor, J., Willinek, W., Limit %P 1435 - 1446 %8 2004/// %G eng %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 %D 2004 %T Számítógépes képfeldolgozás oktatása a Szegedi Tudományegyetemen %X

Az SZTE Informatikai Tanszékcsoportja által gondozott szakoktanterveiben 1993 óta szerepel a képfeldolgozás és alkalmazásainak oktatása. A kreditrendszer bevezetésével a Képfeldolgozás I. tárgy kötelező az ötéves képzésben részt vevő informatikus hallgatóknak. Ezen felül a választható szakirányok között szintén szerepel a Képfeldolgozás szakirány. A szakirányon belül különböző képpfeldolgozási területeket tárgyaló kurzusok épülnek egymásra. Az elméleti megalapozás mellett a képfeldolgozás alkalmazásaira is nagy hangsúlyt fektetünk. A kutatások illetve az orvosi alkalmazások fejlesztése során szerzett eredményeket a kötelező jellegű tárgyak mellett speciálkollégiumok keretében építjül be az otkatási anyagba. Számos hallgatónk választ a képfeldolgzás területéről témát a diplomamunkájához, dolgozataikkal rendszeresen és sikerrel szerepelnek az OTDK-n. Hallgatóink évente több hónapot tölthetnek külföldi partneregyetemeinken, ahol a kutató- és fejlesztőmunka mellett nálunk is elfogadott kurzusokat teljesíthetnek. A képfeldolgozás témakörön belül "ipari" projekt munkákban is egyre több hallgató vesz részt. A doktori programon belül is meghirdetünk képfeldolgozáshoz kapcsolódó kutatási irányokat. Az évente megrendezésre kerülő, 11-éves múltra visszatekintő Képfeldolgozó Nyári Iskolának (SSIP) eddig hatszor adott otthont Szeged. A rendszvénysorozat kiemelkedő fontosságú nemzetközi fórum hallgatóink és oktatóink számára is.

%B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 %I Neumann János Számítógép-tudományi Társaság %C Miskolc %P 191 - 196 %8 Jan 2004 %G eng %0 Journal Article %J RADIOLOGE %D 2003 %T 3D cross section of the laryngotracheal tract. A new method for visualization and quantification of tracheal stenoses %X PURPOSE: Demonstration of a technique for 3D assessment oftracheal stenoses, regarding site, length and degree, based on spiral computed tomography (S-CT). PATIENTS AND METHODS: S-CT scanning and automated segmentation of the laryngo-tracheal tract (LTT) was followed by the extraction of the LTT medial axis using a skeletonisation algorithm. Orthogonal to the medial axis the LTT 3D cross sectional profile was computed and presented as line charts, where degree and length were obtained. Values for both parameters were compared between 36 patients and 18 normal controls separately. Accuracy and precision was derived from 17 phantom studies. RESULTS: Average degree and length of tracheal stenoses were found to be 60.5% and 4.32 cm in patients compared to minor caliber changes of 8.8% and 2.31 cm in normal controls (p <0.005). For the phantoms an excellent correlation between the true and computed 3D cross sectional profile was found (p <0.005) and an accuracy for length and degree measurements of 2.14 mm and 2.53% respectively could be determined. The corresponding figures for the precision were found to be 0.92 mm and 2.56%. CONCLUSION: LTT 3D cross sectional profiles permit objective, accurate and precise assessment of LTT caliber changes. Minor LTT caliber changes can be observed even in normals and, in case of an otherwise normal S-CT study, can be regarded as artefacts. %B RADIOLOGE %V 43 %P 1056 - 1068 %8 2003/// %@ 0033-832X %G eng %N 12 %! RADIOLOGE %0 Journal Article %J RADIOLOGE %D 2003 %T 3D cross section of the laryngotracheal tract. A new method for visualization and quantification of tracheal stenoses %X PURPOSE: Demonstration of a technique for 3D assessment oftracheal stenoses, regarding site, length and degree, based on spiral computed tomography (S-CT). PATIENTS AND METHODS: S-CT scanning and automated segmentation of the laryngo-tracheal tract (LTT) was followed by the extraction of the LTT medial axis using a skeletonisation algorithm. Orthogonal to the medial axis the LTT 3D cross sectional profile was computed and presented as line charts, where degree and length were obtained. Values for both parameters were compared between 36 patients and 18 normal controls separately. Accuracy and precision was derived from 17 phantom studies. RESULTS: Average degree and length of tracheal stenoses were found to be 60.5% and 4.32 cm in patients compared to minor caliber changes of 8.8% and 2.31 cm in normal controls (p <0.005). For the phantoms an excellent correlation between the true and computed 3D cross sectional profile was found (p <0.005) and an accuracy for length and degree measurements of 2.14 mm and 2.53% respectively could be determined. The corresponding figures for the precision were found to be 0.92 mm and 2.56%. CONCLUSION: LTT 3D cross sectional profiles permit objective, accurate and precise assessment of LTT caliber changes. Minor LTT caliber changes can be observed even in normals and, in case of an otherwise normal S-CT study, can be regarded as artefacts. %B RADIOLOGE %V 43 %P 1056 - 1068 %8 2003/// %@ 0033-832X %G eng %N 12 %! RADIOLOGE %0 Journal Article %J Der Radiologe %D 2003 %T 3D-Querschnittsprofil des Laryngotrachealtrakts—Eine neue Methode zur Visualisierung und Quantifizierung von Trachealstenosen %A Sorantin, Erich. %A Halmai, Csongor. %A Balázs Erdőhelyi %A Kálmán Palágyi %A László Gábor Nyúl %A Ollé, Krisztián. %A Geiger, B. %A Lindbichler, F. %A Friedrich, G. %A Kiesler, K. %X

Purpose

Demonstration of a technique for 3D assessment of tracheal stenoses, regarding site, length and degree, based on spiral computed tomography (S-CT).

Patients and Methods

S-CT scanning and automated segmentation of the laryngo-tracheal tract (LTT) was followed by the extraction of the LTT medial axis using a skeletonisation algorithm. Orthogonal to the medial axis the LTT 3D cross sectional profile was computed and presented as line charts, where degree and length were obtained. Values for both parameters were compared between 36 patients and 18 normal controls separately. Accuracy and precision was derived from 17 phantom studies.

Results

Average degree and length of tracheal stenoses were found to be 60.5% and 4.32 cm in patients compared to minor caliber changes of 8.8% and 2.31 cm in normal controls (p <0.005). For the phantoms an excellent correlation between the true and computed 3D cross sectional profile was found (p <0.005) and an accuray for length and degree measurements of 2.14 mm and 2.53% respectively could be determined. The corresponding figures for the precision were found to be 0.92 mm and 2.56%.

Conclusion

LTT 3D cross sectional profiles permit objective, accurate and precise assessment of LTT caliber changes. Minor LTT caliber changes can be observed even in normals and, in case of an otherwise normal S-CT study, can be regarded as artefacts.

 

%B Der Radiologe %I Springer-Verlag %V 43 %P 1056-1068 %8 2003 %G eng %U http://dx.doi.org/10.1007/s00117-003-0990-8 %9 Journal Article %R 10.1007/s00117-003-0990-8 %0 Journal Article %J ACADEMIC RADIOLOGY %D 2003 %T Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function %B ACADEMIC RADIOLOGY %C BAE KT, 1997, RADIOLOGY, V203, P705BENTLEY MD, 1994, CIRC RES, V74, P945 CHULHO W, 2003, J APPL PHYSIOL, V94, P2483 CLARKE LP, 2001, ACAD RADIOL, V8, P447 COXSON H, 2003, AM J RESP CRIT CARE, V167, A81 COXSON H, 2003, AM J RESP CRIT CARE, V167, A81 COXSON %V 10 %P 1104 - 1118 %8 2003/// %@ 1076-6332 %G eng %N 10 %! ACAD RADIOL %0 Book Section %B INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS %D 2003 %T Quantitative analysis of intrathoracic airway trees: Methods and validation %B INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS %I Springer Verlag %C Berlin; HeidelbergBLAND JM, 1986, LANCET, V1, P307BORGEFORS G, 1984, COMPUT VISION GRAPH, V27, P321 CORMEN TH, 1990, INTRO ALGORITHMS GONZALES RC, 1992, DIGITAL IMAGE PROCES KITAOKA H, 1999, J APPL PHYSIOL, V87, P2207 KONG TY, 1989, COMPUT VISION GRAPH, V %P 222 - 233 %8 2003/// %G eng %0 Book Section %B Medical Imaging 2003 %D 2003 %T Quantitative analysis of three-dimensional tubular tree structures %B Medical Imaging 2003 %I SPIE - The International Society for Optical Engineering %C Bellingham; Washington %P 277 - 287 %8 2003/// %G eng %U http://spie.org/x648.html?product_id=459268 %0 Journal Article %J PATTERN RECOGNITION LETTERS %D 2002 %T A 3-subiteration 3D thinning algorithm for extracting medial surfaces %B PATTERN RECOGNITION LETTERS %C BERTRAND G, 1994, P SPIE C VISION GEOM, V2356, P113BERTRAND G, 1995, PATTERN RECOGN LETT, V16, P979 BLUM H, 1967, MODELS PERCEPTION SP, P362 BORGEFORS G, 1984, COMPUT VISION GRAPH, V27, P321 BORGEFORS G, 1999, PATTERN RECOGN, V32, P1225 GERIG G, 1993, LEC %V 23 %P 663 - 675 %8 2002/// %@ 0167-8655 %G eng %N 6 %! PATTERN RECOGN LETT %0 Book Section %B Képfeldolgozók és Alakfelismerők III. Konfereciája %D 2002 %T Digitális képtároló és képtovábbító rendszer (PACS) a Szegedi Tudományegyetemen %B Képfeldolgozók és Alakfelismerők III. Konfereciája %I NJSZT-KÉPAF %C Szeged %P 132 - 139 %8 2002 %G eng %0 Book Section %B Képfeldolgozók és Alakfelismerők III. Konfereciája %D 2002 %T Digitális képtároló és képtovábbító rendszer (PACS) a Szegedi Tudományegyetemen %B Képfeldolgozók és Alakfelismerők III. Konfereciája %I NJSZT-KÉPAF %C Szeged %P 132 - 139 %8 2002/// %G eng %0 Book %D 2002 %T Képfeldolgozók és Alakfelismerők III. Konfereciája %I NJSZT-KÉPAF %C Szeged %8 2002/// %G eng %0 Journal Article %J EUROPEAN RADIOLOGY %D 2002 %T Medical Image Processing, Surgical Planning, Image-Guided Therapy and Robotic Applications: Recent Developments for Radiology %B EUROPEAN RADIOLOGY %V 12 %P 504 %8 2002/// %@ 0938-7994 %G eng %N 1 Suppl %! EUR RADIOL %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 2002 %T Segmentation, skeletonization, and branchpoint matching - A fully automated quantitative evaluation of human intrathoratic airway trees %B LECTURE NOTES IN COMPUTER SCIENCE %V 2489 %P 12 - 19 %8 2002/// %@ 0302-9743 %G eng %! LECT NOTES COMPUT SCI %0 Book Section %B Képfeldolgozók és Alakfelismerők III. Konfereciája %D 2002 %T A sequential 3D curve-thinning algorithm %B Képfeldolgozók és Alakfelismerők III. Konfereciája %I NJSZT-KÉPAF %C Szeged %P 42 - 51 %8 2002/// %G eng %0 Journal Article %J IEEE TRANSACTIONS ON MEDICAL IMAGING %D 2002 %T Spiral-CT-based assessment of tracheal stenoses using 3-D-skeletonization %X PURPOSE: Demonstration of a technique for three-dimensional (3-D) assessment of tracheal-stenoses, regarding site, length and degree, based on spiral computed tomography (S-CT). PATIENTS AND METHODS: S-CT scanning and automated segmentation of the laryngo-tracheal tract (LTT) was followed by the extraction of the LTT medial axis using a skeletonization algorithm. Orthogonal to the medial axis the LTT 3-D cross-sectional profile was computed and presented as line charts, where degree and length was obtained. Values for both parameters were compared between 36 patients and 18 normal controls separately. Accuracy and precision was derived from 17 phantom studies. RESULTS: Average degree and length of tracheal stenoses was found to be 60.5% and 4.32 cm in patients compared with minor caliber changes of 8.8% and 2.31 cm in normal controls (p << 0.0001). For the phantoms an excellent correlation between the true and computed 3-D cross-sectional profile was found (p << 0.005) and an accuracy for length and degree measurements of 2.14 mm and 2.53% respectively could be determined. The corresponding figures for the precision were found to be 0.92 mm and 2.56%. CONCLUSION: LTT 3-D cross-sectional profiles permit objective, accurate and precise assessment of LTT caliber changes. Minor LTT caliber changes can be observed even in normals and, in case of an otherwise normal S-CT study, can be regarded as artifacts. %B IEEE TRANSACTIONS ON MEDICAL IMAGING %V 21 %P 263 - 273 %8 2002/// %@ 0278-0062 %G eng %N 3 %! IEEE T MED IMAGING %0 Book Section %B Informatika a felsőoktatásban %D 2002 %T Számítógépes képfeldolgozás oktatása a Szegedi Tudományegyetemen %X A Szegedi Tudományegyetem tanterveiben 1993 óta szerepel aképfeldolgozás és alkalmazásainak oktatása. A tantárgy ez idő alatt sok változáson ment át. Jelenleg a Képfeldolgozás szakirányt választó hallgatók részesülnek ilyen képzésben. Az adott szakirányon belül különböző képfeldolgozási területek oktatása épül egymásra. Az oktatás során nem csak elméleti és gyakorlati ismereteket szerezhetnek a hallgatók, hanem néhány (főleg orvosi) alkalmazás is bemutatásra kerül. A kötelező jellegű tárgyak mellett speciálkollégiumok engednek bepillantást más kiegészítő területekre. A hallgatók a képfeldolgozás témával rendszeresen vesznek rész helyi és országos Tudományos DIákköri Konferenciákon. Az utóbbi időben sikerült a képfeldolgozásban érdekelt cégekkel felvenni a kapcsolatot, így évente több hallgató vehet részt ipari alkalmazások fejlesztésében. A doktori programon belül is meghirdetünk képfeldolgozáshoz kapcsolódó kutatási irányokat. Ezenkívül rendszeresen megrendezzük a nemzetközi Képfeldolgozó Nyári Iskolákat, ahol nemcsak Magyarországról, hanem a környező országokból is fogadunk hallgatókat és oktatókat. %B Informatika a felsőoktatásban %I Debreceni Egyetem %C Debrecen %P 750 - 757 %8 2002/// %G eng %0 Book Section %B Képfeldolgozók és Alakfelismerők III. Konfereciája %D 2002 %T Többdimenziós MRI képek feldolgozása %B Képfeldolgozók és Alakfelismerők III. Konfereciája %I NJSZT-KÉPAF %C Szeged %P 96 - 97 %8 2002/// %G eng %0 Journal Article %J EUROPEAN SURGERY - ACTA CHIRURGICA AUSTRIACA %D 2002 %T Virtual dissection and automated polyp detection of the colon based on spiral CT - Techniques and preliminary experience on a cadaveric phantom %X Background: CT colonography was found to be sensitive andspecific for detection of colonic polyps and colorectal cancer (CRC). Depending on the software used, CT colonography requires a certain amount of operator interaction, which limits it's widespread usage. The goal of this papers is to present two novel automated techniques for displaying CT colonography: virtual dissection and automated colonic polyp detection. Methods: Virtual dissection refers to a technique where the entire colon is virtually stretched and flattened thus simulating the view on the pathologist's table. Colonic folds show a 'global outward bulging of the contour', whereas colonic polyps exhibit the inverse ('local inward bulging'). This feature is used to map areas of 'local inward bulging' with colours on 3D reconstructions. A cadaveric phantom with 13 artificially inserted polyps was used for validation of both techniques. Results: On virtual dissection all 13 inserted polyps could be identified. They appeared either as bumps or as local broadening of colonic folds. In addition, the automated colonic polyp detection algorithm was able to tag all polyps. Only 10 min of operator interaction were necessary for both techniques. Conclusions: Virtual dissection overcomes the shortcomings of CT colonography, and automated colonic polyp detection establishes a roadmap of the polyps. %B EUROPEAN SURGERY - ACTA CHIRURGICA AUSTRIACA %V 34 %P 143 - 149 %8 2002/// %@ 1682-8631 %G eng %N 2 %! EUR SURG-ACA %0 Book Section %B Képfeldolgozók és Alakfelismerők III. Konfereciája %D 2002 %T Virtual Dissection of the Colon %B Képfeldolgozók és Alakfelismerők III. Konfereciája %I NJSZT-KÉPAF %C Szeged %P 109 - 117 %8 2002/// %G eng %0 Book Section %B 3D Image Processing %D 2002 %T Virtual Dissection of the Colon %B 3D Image Processing %I Springer-Verlag %C New York %P 197 - 209 %8 2002/// %G eng %0 Book Section %B Medical Imaging 2002: Visualization, Image-Guided Procedures, and Display %D 2002 %T Virtual dissection of the colon: technique and first experiments with artificial and cadaveric phantoms %X Virtual dissection refers to a display technique for polypdetection, where the colon is digitally straightened and then flattened using multirow detector Computed Tomograph (CT) images. As compared to virtual colonoscopy where polyps may be hidden from view behind the folds, the unravelled colon is more suitable for polyp detection, because the entire inner surface of the colon is displayed in a single view. The method was tested both on artificial and cadaveric phantoms. All polyps could be recognized on both phantoms. This technique for virtual dissection requires only a minimum of operator interaction. %B Medical Imaging 2002: Visualization, Image-Guided Procedures, and Display %I SPIE %C Bellingham; Washington %P 713 - 721 %8 2002/// %G eng %0 Journal Article %J Acta Cybernetica %D 2001 %T A 3D parallel shrinking algorithm %A Kálmán Palágyi %X

Shrinking is a frequently used preprocessing step in image processing. This paper presents an efficient 3D parallel shrinking algorithm for transforming a binary object into its topological kernel. The applied strategy is called directional: each iteration step is composed of six subiterations each of which can be executed in parallel. The algorithm makes easy implementation possible, since deletable points are given by 3x3x3 matching templates. The topological correctness of the algorithm is proved for (26,6) binary pictures.

%B Acta Cybernetica %I University of Szeged %C Szeged %V 15 %P 201-211 %G eng %9 Journal Article %0 Journal Article %J ACTA CYBERNETICA-SZEGED %D 2001 %T A 3D parallel shrinking algorithm %B ACTA CYBERNETICA-SZEGED %V 15 %P 201 - 211 %8 2001 %@ 0324-721X %G eng %N 2 %! ACTA CYBERN-SZEGED %0 Journal Article %J ACTA CYBERNETICA-SZEGED %D 2001 %T Affine matching of two sets of points in arbitrary dimensions. %B ACTA CYBERNETICA-SZEGED %V 15 %P 101 - 106 %8 2001 %@ 0324-721X %G eng %N 1 %! ACTA CYBERN-SZEGED %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 2001 %T A sequential 3D thinning algorithm and its medical applications %B LECTURE NOTES IN COMPUTER SCIENCE %V 2082 %P 409 - 415 %8 2001/// %@ 0302-9743 %G eng %U http://www.springerlink.com/content/py49qu0e434n0n16 %! LECT NOTES COMPUT SCI %0 Book Section %B Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis, ISPA 2001, Pula, Croatia %D 2001 %T Virtual Dissection of the Colon Based on Helical CT Data - Can It Be Done? %X Colorectal cancer is the third most commonly diagnosed cancer;and colonic polyps are known precursors of that particular cancer. Virtual dissection refers to a display technique for polyp detection based on helical CT data, where the colon is dissected and flattened as on the pathologist's table. The approach and image processing as well as the early experience are described in this paper. %B Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis, ISPA 2001, Pula, Croatia %I University of Zagreb %C Zagreb %P 224 - 229 %8 2001/// %G eng %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 2000 %T A 3D 3-subiteration thinning algorithm for medial surfaces %B LECTURE NOTES IN COMPUTER SCIENCE %C BERTRAND G, 1994, P SPIE C VISION GEOM, V2356, P113BERTRAND G, 1995, PATTERN RECOGN LETT, V16, P979 BLU H, 1967, MODELS PERCEPTION SP, P362 GONG WX, 1990, P 10 INT C PATT REC, P188 KONG TY, 1989, COMPUT VISION GRAPH, V48, P357 KONG TY, 1995, INT J PATTERN %V 1953 %P 406 - 418 %8 2000/// %@ 0302-9743 %G eng %! LECT NOTES COMPUT SCI %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2000 %D 2000 %T 3D vékonyítás és alkalmazása vérerek és légutak átmérőjének meghatározására %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2000 %I NJSZT %C Noszvaj %P 95 - 100 %8 Jan 2000 %G eng %0 Book Section %B Digital (R)Evolution in Radiology %D 2000 %T New advances for imaging of laryngotracheal stenosis by post processing of spiral-CT data %B Digital (R)Evolution in Radiology %I Springer-Verlag %C Berlin; Heidelberg; New York; London; Paris; Tokyo %P 275 - 285 %8 2000/// %G eng %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 2000 %T Point-based registration assuming affine motion %B LECTURE NOTES IN COMPUTER SCIENCE %V 1888 %P 329 - 338 %8 2000 %@ 0302-9743 %G eng %U http://www.inf.u-szeged.hu/ipcg/publications/papers/Tanacs_2000_AFPAC.pdf %! LECT NOTES COMPUT SCI %0 Journal Article %J TASK QUARTERLY %D 1999 %T 3D thinning and its applications to medical image processing %B TASK QUARTERLY %V 3 %P 397 - 408 %8 1999/// %@ 1428-6394 %G eng %N 4 %! TASK Q %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 1999 %T Directional 3D thinning using 8 subiterations %B LECTURE NOTES IN COMPUTER SCIENCE %C BERTRAND G, 1994, P SPIE C VISION GEOM, V2356, P113BERTRAND G, 1995, PATTERN RECOGN LETT, V16, P979 GONG WX, 1990, P 10 INT C PATT REC, P188 KONG TY, 1989, COMPUT VISION GRAPH, V48, P357 KONG TY, 1995, INT J PATTERN RECOGN, V9, P813 LEE TC, 1994, CVGIP-GR %V 1568 %P 325 - 336 %8 1999/// %@ 0302-9743 %G eng %! LECT NOTES COMPUT SCI %0 Journal Article %J GRAPHICAL MODELS AND IMAGE PROCESSING %D 1999 %T A parallel 3D 12-subiteration thinning algorithm %B GRAPHICAL MODELS AND IMAGE PROCESSING %C BERTRAND G, 1994, P SPIE C VISION GEOM, V2356, P113BERTRAND G, 1995, PATTERN RECOGN LETT, V16, P979 BLUM H, 1967, MODELS PERCEPTION SP, P362 BORGEFORS G, 1984, COMPUT VISION GRAPH, V27, P321 CALABI L, 1965, 60429 PARK MATH LAB GERIG G, 1993, LECT NOTES CO %V 61 %P 199 - 221 %8 1999/// %@ 1077-3169 %G eng %U http://www.inf.u-szeged.hu/ipcg/publications/papers/PalagyiKuba_GMIP1999.pdf %N 4 %! GRAPH MODEL IM PROC %0 Conference Paper %B International Workshop on Biomedical Image Registration (WBIR) %D 1999 %T Target registration error of point-based methods assuming rigid-body and linear motions %B International Workshop on Biomedical Image Registration (WBIR) %I Slovenian Society of Informatics %C Ljubljana %P 223 - 233 %8 Aug 1999 %G eng %0 Journal Article %J PATTERN RECOGNITION LETTERS %D 1998 %T A 3D 6-subiteration thinning algorithm for extracting medial lines %B PATTERN RECOGNITION LETTERS %C BERTRAND G, 1994, P SPIE C VISION GEOM, V2356, P113BERTRAND G, 1995, PATTERN RECOGN LETT, V16, P979 BLUM H, 1967, MODELS PERCEPTION SP, P362 GONG WX, 1990, P 10 INT C PATT REC, P188 KONG TY, 1989, COMPUT VISION GRAPH, V48, P357 LEE TC, 1994, CVGIP-GRAPH M %V 19 %P 613 - 627 %8 1998/// %@ 0167-8655 %G eng %N 7 %! PATTERN RECOGN LETT %0 Journal Article %J CIT JOURNAL OF COMPUTING AND INFORMATION TECHNOLOGY %D 1998 %T A hybrid thinning algorithm for 3D medical images %B CIT JOURNAL OF COMPUTING AND INFORMATION TECHNOLOGY %V 6 %P 149 - 164 %8 1998/// %@ 1330-1136 %G eng %N 2 %! J COMPUT INF TECHNOL (CIT) %0 Journal Article %J MACHINE GRAPHICS AND VISION %D 1998 %T Medical image registration based on interactively identified anatomical landmark points %B MACHINE GRAPHICS AND VISION %V 7 %P 151 - 158 %8 1998/// %@ 1230-0535 %G eng %N 1/2 %! MACH GRAPH VIS %0 Journal Article %J MACHINE GRAPHICS AND VISION %D 1998 %T Medical image registration based on interactively identified anatomical landmark points %B MACHINE GRAPHICS AND VISION %V 7 %P 151 - 158 %8 1998 %@ 1230-0535 %G eng %N 1/2 %! MACH GRAPH VIS %0 Conference Paper %B XXI. Neumann Kollokvium kiadványa %D 1998 %T Pont alapú regisztráció, képfúzió %B XXI. Neumann Kollokvium kiadványa %I Neumann János Számítógép-tudományi Társaság %C Budapest %P 67 - 70 %8 Nov 1998 %G eng %0 Conference Paper %B XXI. Neumann Kollokvium kiadványa %D 1998 %T Pont alapú regisztráció, képfúzió %B XXI. Neumann Kollokvium kiadványa %I Neumann János Számítógép-tudományi Társaság %C Budapest %P 67 - 70 %8 Nov 1998 %G eng %0 Conference Paper %B XXI. Neumann Kollokvium kiadványa %D 1998 %T Vékonyító algoritmusok 3D orvosi képekre %B XXI. Neumann Kollokvium kiadványa %I Neumann János Számítógép-tudományi Társaság %C Budapest %P 63 - 66 %8 Nov 1998 %G eng %0 Conference Paper %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 1997 %D 1997 %T An algorithm for thinning 3D medical images %B A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 1997 %I Pannon Agrártudományi Egyetem Georgikon Mezőgazdaságtudományi Kar %C Keszthely %P 64 - 71 %8 Oct 1997 %G eng %0 Conference Paper %B Magyar Képfeldolgozók és Alakfelismerők Országos Konferenciája %D 1997 %T Orvosi képek regisztrációja interaktívan kijelölt anatómiai pontok alapján %B Magyar Képfeldolgozók és Alakfelismerők Országos Konferenciája %I Pannon Agrártudományi Egyetem Georgikon Mezőgazdaságtudományi Kar %C Keszthely %P 1 - 8 %8 Oct 1997 %G eng %0 Conference Paper %B Magyar Képfeldolgozók és Alakfelismerők Országos Konferenciája %D 1997 %T Orvosi képek regisztrációja interaktívan kijelölt anatómiai pontok alapján %B Magyar Képfeldolgozók és Alakfelismerők Országos Konferenciája %I Pannon Agrártudományi Egyetem Georgikon Mezőgazdaságtudományi Kar %C Keszthely %P 1 - 8 %8 Oct 1997 %G eng %0 Book Section %B Computer analysis of images and patterns %D 1997 %T A parallel 12-subiteration 3D thinning algorithm to extract medial lines %B Computer analysis of images and patterns %I Springer %C Berlin %P 400 - 407 %8 1997/// %G eng %0 Book Section %B INFORMATION PROCESSING IN MEDICAL IMAGING %D 1997 %T A thinning algorithm to extract medial lines from 3D medical images %B INFORMATION PROCESSING IN MEDICAL IMAGING %I Springer Verlag %C Berlin; HeidelbergGERIG G, 1993, LECT NOTES COMPUTER, V687, P94GONG WX, 1990, P 10 INT C PATT REC, P188 KONG TY, 1989, COMPUT VISION GRAPH, V48, P357 LEE TC, 1994, CVGIP-GRAPH MODEL IM, V6, P462 MA CM, 1994, CVGIP-IMAG UNDERSTAN, V59, P328 PALAGYI K, 1996 %P 411 - 416 %8 1997/// %G eng %0 Conference Paper %B International EuroPACS Meeting, EuroPACS '96 %D 1996 %T DICOM Based PACS and Its Application in the Education %X

SZOTE-PACS is a DICOM based PACS developed at the Universitiesof Szeged. It is able to collect studies from different modalities and convert them into DICOM format. The DICOM studies can be edited, modified by RIS data, then verified and transferred into the archiving server. There is a graphic application based on Oracle for searching and other database management functions of the Archive. The archived studies can be presented and/or processed on the viewing workstations. SZOTE- PACS also supports the creation and presentation of educational materials fror medical students.

%B International EuroPACS Meeting, EuroPACS '96 %P 46 - 49 %8 Oct 1996 %G eng %9 Conference paper %0 Conference Paper %B International EuroPACS Meeting, EuroPACS '96 %D 1996 %T DICOM Based PACS and Its Application in the Education %X

SZOTE-PACS is a DICOM based PACS developed at the Universitiesof Szeged. It is able to collect studies from different modalities and convert them into DICOM format. The DICOM studies can be edited, modified by RIS data, then verified and transferred into the archiving server. There is a graphic application based on Oracle for searching and other database management functions of the Archive. The archived studies can be presented and/or processed on the viewing workstations. SZOTE- PACS also supports the creation and presentation of educational materials fror medical students.

%B International EuroPACS Meeting, EuroPACS '96 %P 46 - 49 %8 Oct 1996 %G eng %0 Conference Paper %B SUMMER WORKSHOP ON COMPUTATIONAL MODELLING, IMAGING AND VISUALIZATION IN BIOSCIENCES (COMBIO) %D 1996 %T Medical image registration based on fuzzy objects %B SUMMER WORKSHOP ON COMPUTATIONAL MODELLING, IMAGING AND VISUALIZATION IN BIOSCIENCES (COMBIO) %I KFKI %C Budapest %P 44 - 48 %8 1996.08.29 %G eng %0 Conference Paper %B A számítástechnika orvosi és biológiai alkalmazásai: A XX. Neumann Kollokvium Kiadványa %D 1996 %T Orvosi képek fuzzy objektumokon alapuló regisztrációja %B A számítástechnika orvosi és biológiai alkalmazásai: A XX. Neumann Kollokvium Kiadványa %I NJSZT %C Budapest %P 107 - 110 %8 Nov 1996 %G eng %0 Conference Paper %B A számítástechnika orvosi és biológiai alkalmazásai: A XX. Neumann Kollokvium Kiadványa %D 1996 %T SZOTE-PACS: A Szent-Györgyi Albert Orvostudományi Egyetem képarchiváló és továbbító rendszerének szoftvere %X

A Szent-Györgyi Albert Orvostudományi Egyetem kép-archiváló és -továbbító rendszer (SZOTE-PACS) szoftverének a fejlesztését ismertetjük előadásunkban. A cél egy olyan számítógépes hálózat elkészítése, amely nemcsak a klinikai vizsgálatok képeinek tárolásával és átvitelével kapcsolatos feladatokat látja el, de támogatja az oktatási és konzultációs tevékenységéeket is. A SZOTE-PACS 3 részre bontható: képfelvevő, archiváló és megjelenítő állomásokra. A képfelvevő munkaállomásoknak kettős feladata van: egyrészt a különféle modalitásokon (CT, MR, NM, US és SPECT) vagy röntgenfilm-scanneren felvett, illetve a DICOM- szabványnak megfelelő állomásról beérkező vizsgálatok begyűjtése, másrészt az Interfile 3.3, ACR-NEMA 2.0 vagy TIFF formátumú vizsgálatok DICOM formátumra való automatikus konvertálása. A rendszer képes a Radiológiai Klinika Információs Rendszerében (RIS) levő információk átvételére és beépítésére is. Az így előkészített vizsgálatok átküldhetők a központi szerverre, ahol azok az archívumban automatiksan tárolódnak. A jelenlegi diszk kapacitás mellett 15 napig őrizzük a vizsgálatokat. A tervek szerint 15 nap után csak a képeket töröljük a szerverről, a vizsgálat egyéb (nem képi) adatai továbbra is megőrzésre kerülnek. Az archívumban Oracle adatbázis kezeéő rendszer segíti a visszakeresést, a mejelenítést és a módosítást. A feldolgozó munkaállomásokra (PC-k, UNOX-állomások vagy X-terminálok) kérheti le a felhasználó a szerveren tárolt vizsgálatokat. Itt jeleníthetők meg illetve dolgozhatók fel a vizsgálatok képei. Az orvostanhallgatók és doktoranduszok képzésére HTML-ben írt oktatási anyagok állíthatók össze a tárolt szöveges és képi adatokból. Az oktatási anyagokat a rendszer külön adatbázisban tárolja.

%B A számítástechnika orvosi és biológiai alkalmazásai: A XX. Neumann Kollokvium Kiadványa %I NJSZT %C Veszprém %P 173 - 176 %8 Nov 1996 %G eng %0 Conference Paper %B A számítástechnika orvosi és biológiai alkalmazásai: A XX. Neumann Kollokvium Kiadványa %D 1996 %T SZOTE-PACS: A Szent-Györgyi Albert Orvostudományi Egyetem képarchiváló és továbbító rendszerének szoftvere %X

A Szent-Györgyi Albert Orvostudományi Egyetem kép-archiváló és -továbbító rendszer (SZOTE-PACS) szoftverének a fejlesztését ismertetjük előadásunkban. A cél egy olyan számítógépes hálózat elkészítése, amely nemcsak a klinikai vizsgálatok képeinek tárolásával és átvitelével kapcsolatos feladatokat látja el, de támogatja az oktatási és konzultációs tevékenységéeket is. A SZOTE-PACS 3 részre bontható: képfelvevő, archiváló és megjelenítő állomásokra. A képfelvevő munkaállomásoknak kettős feladata van: egyrészt a különféle modalitásokon (CT, MR, NM, US és SPECT) vagy röntgenfilm-scanneren felvett, illetve a DICOM- szabványnak megfelelő állomásról beérkező vizsgálatok begyűjtése, másrészt az Interfile 3.3, ACR-NEMA 2.0 vagy TIFF formátumú vizsgálatok DICOM formátumra való automatikus konvertálása. A rendszer képes a Radiológiai Klinika Információs Rendszerében (RIS) levő információk átvételére és beépítésére is. Az így előkészített vizsgálatok átküldhetők a központi szerverre, ahol azok az archívumban automatiksan tárolódnak. A jelenlegi diszk kapacitás mellett 15 napig őrizzük a vizsgálatokat. A tervek szerint 15 nap után csak a képeket töröljük a szerverről, a vizsgálat egyéb (nem képi) adatai továbbra is megőrzésre kerülnek. Az archívumban Oracle adatbázis kezeéő rendszer segíti a visszakeresést, a mejelenítést és a módosítást. A feldolgozó munkaállomásokra (PC-k, UNOX-állomások vagy X-terminálok) kérheti le a felhasználó a szerveren tárolt vizsgálatokat. Itt jeleníthetők meg illetve dolgozhatók fel a vizsgálatok képei. Az orvostanhallgatók és doktoranduszok képzésére HTML-ben írt oktatási anyagok állíthatók össze a tárolt szöveges és képi adatokból. Az oktatási anyagokat a rendszer külön adatbázisban tárolja.

%B A számítástechnika orvosi és biológiai alkalmazásai: A XX. Neumann Kollokvium Kiadványa %I NJSZT %C Veszprém %P 173 - 176 %8 Nov 1996 %G eng %0 Book Section %B Informatika a felsőoktatásban '96 és Networkshop '96 %D 1996 %T A többdimenziós képfeldolgozás programjai és oktatásuk %X Nowdays, the multidimensional (i.e. higher than 2-dimensional)image processing has been a strongly developing area. One of its most important application areas is the medicine, where numerous diagnostic imaging devices (e.g., CT, MR, SPECT etc.) are able to produce 3- or even higher dimensional images. We have studied the possibility of introduction of multidimensional image processing into the subjects of Image Processing at József Attila University. First, we considered the methods of generation of such images, then the different standards accepted in the medical applications. From the processing algorithms we have dealt with the 3D skeletons, binary operations, reconstruction and registration. These topics are discussed in the education of graduated and PhD students as well. %B Informatika a felsőoktatásban '96 és Networkshop '96 %I Debreceni Egyetem %C Debrecen %P 649 - 656 %8 1996/// %G eng %0 Book Section %B Informatika a felsőoktatásban '96 és Networkshop '96 %D 1996 %T A többdimenziós képfeldolgozás programjai és oktatásuk %X Nowdays, the multidimensional (i.e. higher than 2-dimensional)image processing has been a strongly developing area. One of its most important application areas is the medicine, where numerous diagnostic imaging devices (e.g., CT, MR, SPECT etc.) are able to produce 3- or even higher dimensional images. We have studied the possibility of introduction of multidimensional image processing into the subjects of Image Processing at József Attila University. First, we considered the methods of generation of such images, then the different standards accepted in the medical applications. From the processing algorithms we have dealt with the 3D skeletons, binary operations, reconstruction and registration. These topics are discussed in the education of graduated and PhD students as well. %B Informatika a felsőoktatásban '96 és Networkshop '96 %I Debreceni Egyetem %C Debrecen %P 649 - 656 %8 1996 %G eng %0 Conference Paper %B 4th International Workshop Measurement %D 1995 %T Presentation of 3D SPECT images %X

The problem of presentation of 3D SPECT (Single-Photon EmissionComputed Tomography) images are considered. Instead of the classical 2D image presentation methods (displaying the slices) the following methods are studied: presentation of sections with a 3D reference image, generation of 3D phase and amplitude images (for gated heart studies), surface rendering and volume rendering by 3DVIEWNIX (MIGP, Univ. Pennsylvania) software. The projections are collected by a single-head SPECT system. After preprocessing (centre-of-rotation, uniformity correction) and reconstruction of the transversal sections absorption- correction and special 3D processing can be done. There are clinical programs for the different kinds of studies (e.g. brain SPECT, heart SPECT). The processed section images are stored and converted into Interfile 3.3 format. The first two presentation methods are available on our SPECT system. In order to use the 3DVIEWNIX software the file of the reconstructed sections is converted into a generalized ACR-NEMA format and transferred into our university network. The 3DVIEWNIX system runs on UNIX machines. It is suitable to visualize, manipulate and analyse multidimensional image data like SPECT. The results of the surface and volume rendering of brain and heart studies are presented.

%B 4th International Workshop Measurement %C Smolenice, Slovakia %P 82 %8 May 1995 %G eng %0 Conference Paper %B 4th International Workshop Measurement %D 1995 %T Presentation of 3D SPECT images %X

The problem of presentation of 3D SPECT (Single-Photon EmissionComputed Tomography) images are considered. Instead of the classical 2D image presentation methods (displaying the slices) the following methods are studied: presentation of sections with a 3D reference image, generation of 3D phase and amplitude images (for gated heart studies), surface rendering and volume rendering by 3DVIEWNIX (MIGP, Univ. Pennsylvania) software. The projections are collected by a single-head SPECT system. After preprocessing (centre-of-rotation, uniformity correction) and reconstruction of the transversal sections absorption- correction and special 3D processing can be done. There are clinical programs for the different kinds of studies (e.g. brain SPECT, heart SPECT). The processed section images are stored and converted into Interfile 3.3 format. The first two presentation methods are available on our SPECT system. In order to use the 3DVIEWNIX software the file of the reconstructed sections is converted into a generalized ACR-NEMA format and transferred into our university network. The 3DVIEWNIX system runs on UNIX machines. It is suitable to visualize, manipulate and analyse multidimensional image data like SPECT. The results of the surface and volume rendering of brain and heart studies are presented.

%B 4th International Workshop Measurement %C Smolenice, Slovakia %P 82 %8 May 1995 %G eng %0 Book Section %B Proceedings of the 9th Scandinavian Conference on Image Analysis, SCIA '95 %D 1995 %T Signature verification using neuron nets %B Proceedings of the 9th Scandinavian Conference on Image Analysis, SCIA '95 %I World Sci. Publishing, River Edge, NJ %C River Edge %P 1115 - 1122 %8 1995/// %G eng %0 Book Section %B MEDICOMP '94, Számítástechnikai és kibernetikai módszerek az orvostudományban és a biológiában %D 1994 %T Szabványos képformák orvosi képek tárolására %X Az orvosi képalkotó berendezések fejlődésével elengedhetetlennévált a szabványos orvosi képformátumok kialakítása. A különféle eszközökön készült felvételek feldolgozását, összehasonlítását és hálózatban való továbbítását megnehezítette, hogy a gyártók a képeket csak egyéni, többé-kevésbé publikált formátumban tárolták. Ezen a helyzeten kívánnak változtatni különféle szervezetek olyan szabványok bevezetésével, amelyek speciálisan orvosi képek esetében lehetnek hasznosak. A szabványosítási törekvések eredményeként mára három nagy irányzat alakult ki: ACR-NEMA, DICOM és Interfile. Előadásunkban vázoljuk az orvosi képek tárolási formátumainál érvényesülő specifikus szempontokat, röviden ismertetjük az említett szabványokat és bemutatjuk az általunk eddig készített, a különféle formátumok közötti konverziót biztosító programokat. %B MEDICOMP '94, Számítástechnikai és kibernetikai módszerek az orvostudományban és a biológiában %I SZOTE %C Szeged %P 112 - 116 %8 1994/// %G eng %0 Book Section %B MEDICOMP '94, Számítástechnikai és kibernetikai módszerek az orvostudományban és a biológiában %D 1994 %T Szabványos képformák orvosi képek tárolására %X Az orvosi képalkotó berendezések fejlődésével elengedhetetlennévált a szabványos orvosi képformátumok kialakítása. A különféle eszközökön készült felvételek feldolgozását, összehasonlítását és hálózatban való továbbítását megnehezítette, hogy a gyártók a képeket csak egyéni, többé-kevésbé publikált formátumban tárolták. Ezen a helyzeten kívánnak változtatni különféle szervezetek olyan szabványok bevezetésével, amelyek speciálisan orvosi képek esetében lehetnek hasznosak. A szabványosítási törekvések eredményeként mára három nagy irányzat alakult ki: ACR-NEMA, DICOM és Interfile. Előadásunkban vázoljuk az orvosi képek tárolási formátumainál érvényesülő specifikus szempontokat, röviden ismertetjük az említett szabványokat és bemutatjuk az általunk eddig készített, a különféle formátumok közötti konverziót biztosító programokat. %B MEDICOMP '94, Számítástechnikai és kibernetikai módszerek az orvostudományban és a biológiában %I SZOTE %C Szeged %P 112 - 116 %8 1994 %G eng %0 Journal Article %J ALKALMAZOTT MATEMATIKAI LAPOK %D 1993 %T Lokális párhuzamos eljárás bináris képek zajszűrésére %B ALKALMAZOTT MATEMATIKAI LAPOK %V 17 %P 373 - 396 %8 1993/// %@ 0133-3399 %G eng %! ALKALMAZOTT MATEMATIKAI LAPOK %0 Book Section %B Proceedings of Conference on Intelligent Systems, CIS ’91 %D 1991 %T Image processing on cellprocessors %B Proceedings of Conference on Intelligent Systems, CIS ’91 %I NJSZT %C Budapest %P 31 - 40 %8 1991/// %G eng %0 Book Section %B Proceedings of Conference on Intelligent Systems, CIS ’91 %D 1991 %T Neural Network Implementation on Cellular Processor %B Proceedings of Conference on Intelligent Systems, CIS ’91 %I NJSZT %C Budapest %P 129 - 137 %8 1991/// %G eng %0 Book Section %B Proceedings of the 5th International Workshop Parallel Processing by Cellular Automata and Arrays, Parcella '90 %D 1990 %T Cellular program development for the M1 processor %B Proceedings of the 5th International Workshop Parallel Processing by Cellular Automata and Arrays, Parcella '90 %I Akademie Verlag %C Berlin %P 315 - 319 %8 1990/// %G eng %0 Journal Article %J LECTURE NOTES IN COMPUTER SCIENCE %D 1989 %T SOLUTION OF DENSE SYSTEMS OF LINEAR-EQUATIONS USING CELLULAR PROCESSORS %B LECTURE NOTES IN COMPUTER SCIENCE %C BOYANCZYK A, 1981, NUMERICALLY STABLE S, P21HWANG K, 1982, IEEE T COMPUT, V31, P1215 KATONA E, 1986, PARALLEL COMPUTING 8 KATONA E, 1988, 4TH P CELL M TU BRAU KUNG HT, 1978, SYSTOLIC ARRAYS, P32 LEGENDI T, 1977, CELLPROCESSORS COMPU, V11, P147 MIKLOSKO J, %V 342 %P 311 - 316 %8 1989/// %@ 0302-9743 %G eng %! LECT NOTES COMPUT SCI %0 Book Section %B Proceedings of the 3rd International Workshop Parallel Processing by Cellular Automata and Arrays, Parcella'86 %D 1987 %T Cellular algorithms for matrix multiplication %B Proceedings of the 3rd International Workshop Parallel Processing by Cellular Automata and Arrays, Parcella'86 %I North-Holland Publishing Company %C Amsterdam %P 122 - 129 %8 1987/// %G eng