TY - CHAP T1 - Collaborative Mobile 3D Reconstruction of Urban Scenes T2 - Proceedings of the ACCV Workshop on Intelligent Mobile and Egocentric Vision (ACCV-IMEV), Lecture Notes in Computer Science Y1 - 2015 A1 - Attila Tanacs A1 - András Majdik A1 - Levente Hajder A1 - Jozsef Molnar A1 - Zsolt Santa A1 - Zoltan Kato ED - Chu-Song Chen ED - Mohan Kankanhall ED - Shang-Hong Lai ED - Joo Hwee JF - Proceedings of the ACCV Workshop on Intelligent Mobile and Egocentric Vision (ACCV-IMEV), Lecture Notes in Computer Science PB - Springer CY - Singapore ER - TY - JOUR T1 - Estimation of linear deformations of 2D and 3D fuzzy objects JF - PATTERN RECOGNITION Y1 - 2015 A1 - Attila Tanacs A1 - Joakim Lindbald A1 - Nataša Sladoje A1 - Zoltan Kato AB -

Registration is a fundamental task in image processing, it is used to determine geometric correspondences between images taken at different times and/or from different viewpoints. Here we propose a general framework in n-dimensions to solve binary shape/object matching problems without the need of establishing additional point or other type of correspondences. The approach is based on generating and solving polynomial systems of equations. We also propose an extension which, provided that a suitable segmentation method can produce a fuzzy border representation, further increases the registration precision. Via numerous synthetic and real test we examine the different solution techniques of the polynomial systems of equations. We take into account a direct analytical, an iterative least-squares, and a combined method. Iterative and combined approaches produce the most precise results. Comparison is made against competing methods for rigid-body problems. Our method is orders of magnitude faster and is able to recover alignment regardless of the magnitude of the deformation compared to the narrow capture range of others. The applicability of the proposed methods is demonstrated on real X-ray images of hip replacement implants and 3D CT volumes of the pelvic area. Since the images must be parsed through only once, our approach is especially suitable for solving registration problems of large images.

PB - Elsevier VL - 48 IS - 4 ER - TY - JOUR T1 - Realigning 2D and 3D Object Fragments without Correspondences JF - Pattern Analysis and Machine Intelligence, IEEE Transactions on Y1 - 2015 A1 - Csaba Domokos A1 - Zoltan Kato AB -

This paper addresses the problem of simultaneous estimation of different linear deformations, resulting in a global non-linear transformation, between an original object and its broken fragments. A general framework is proposed without using correspondences, where the solution of a polynomial system of equations directly provides the parameters of the alignment. We quantitatively evaluate the proposed algorithm on a large synthetic dataset containing 2D and 3D images, where linear (rigid-body and affine) transformations are considered. We also conduct an exhaustive analysis of the robustness against segmentation errors and the numerical stability of the proposed method. Moreover, we present experiments on 2D real images as well as on volumetric medical images.

 

PB - IEEE VL - pp IS - 99 ER - TY - CONF T1 - 3D Reconstruction of Planar Patches Seen by Omnidirectional Cameras T2 - International Conference on Digital Image Computing: Techniques and Applications (DICTA) Y1 - 2014 A1 - Jozsef Molnar A1 - Robert Frohlich A1 - Chetverikov Dmitrij A1 - Zoltan Kato ED - Abdesselam Bouzerdoum ED - Lei Wang ED - Philip Ogunbona ED - Wanqing Li ED - Son Lam Phung JF - International Conference on Digital Image Computing: Techniques and Applications (DICTA) PB - IEEE CY - Wollongong, Australia ER - TY - CHAP T1 - 3D Reconstruction of Planar Surface Patches: A Direct Solution T2 - Proceedings of the ACCV Workshop on Big Data in 3D Computer Vision (ACCV-BigData3DCV) Y1 - 2014 A1 - Jozsef Molnar A1 - Rui Huang A1 - Zoltan Kato ED - Jian Zhang ED - Mohammed Bennamoun ED - Fatih Porikli JF - Proceedings of the ACCV Workshop on Big Data in 3D Computer Vision (ACCV-BigData3DCV) PB - Springer CY - Singapore, Szingapúr ER - TY - CONF T1 - Affine Alignment of Occluded Shapes T2 - International Conference on Pattern Recognition (ICPR) Y1 - 2014 A1 - Zsolt Santa A1 - Zoltan Kato ED - Michael Felsberg JF - International Conference on Pattern Recognition (ICPR) PB - IEEE CY - Stockholm, Svédország SN - 978-4-9906441-0-9 ER - TY - CONF T1 - Establishing Correspondences between Planar Image Patches T2 - International Conference on Digital Image Computing: Techniques and Applications (DICTA) Y1 - 2014 A1 - Attila Tanacs A1 - András Majdik A1 - Jozsef Molnar A1 - Atul Rai A1 - Zoltan Kato ED - Abdesselam Bouzerdoum ED - Lei Wang ED - Philip Ogunbona ED - Wanqing Li ED - Son Lam Phung JF - International Conference on Digital Image Computing: Techniques and Applications (DICTA) PB - IEEE CY - Wollongong, Australia ER - TY - CHAP T1 - Képfeldolgozás a szegedi informatikus-képzésben T2 - Informatika a felsőoktatásban 2014 Y1 - 2014 A1 - Péter Balázs A1 - Endre Katona A1 - Zoltan Kato A1 - Antal Nagy A1 - Gábor Németh A1 - László Gábor Nyúl A1 - Kálmán Palágyi A1 - Attila Tanacs A1 - László Gábor Varga ED - Roland Kunkli ED - Ildikó Papp ED - Edéné Rutkovszky JF - Informatika a felsőoktatásban 2014 PB - University of Debrecen CY - Debrecen, Hungary ER - TY - CONF T1 - 2D és 3D bináris objektumok lineáris deformáció-becslésének numerikus megoldási lehetőségei T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 Y1 - 2013 A1 - Attila Tanacs A1 - Joakim Lindblad A1 - Nataša Sladoje A1 - Zoltan Kato ED - László Czúni JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2013 PB - NJSZT-KÉPAF CY - Veszprém ER - TY - CONF T1 - Correspondence-less non-rigid registration of triangular surface meshes T2 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Y1 - 2013 A1 - Zsolt Santa A1 - Zoltan Kato AB -

A novel correspondence-less approach is proposed to find a thin plate spline map between a pair of deformable 3D objects represented by triangular surface meshes. The proposed method works without landmark extraction and feature correspondences. The aligning transformation is found simply by solving a system of nonlinear equations. Each equation is generated by integrating a nonlinear function over the object's domains. We derive recursive formulas for the efficient computation of these integrals. Based on a series of comparative tests on a large synthetic dataset, our triangular mesh-based algorithm outperforms state of the art methods both in terms of computing time and accuracy. The applicability of the proposed approach has been demonstrated on the registration of 3D lung CT volumes. © 2013 IEEE.

JF - IEEE Conference on Computer Vision and Pattern Recognition (CVPR) PB - IEEE CY - Portland, OR, USA N1 - ScopusID: 84887348013doi: 10.1109/CVPR.2013.295 ER - TY - CHAP T1 - Elastic Registration of 3D Deformable Objects T2 - Proceedings of International Conference on Digital Image Computing: Techniques and Applications (DICTA) Y1 - 2013 A1 - Zsolt Santa A1 - Zoltan Kato ED - Geoff West ED - Péter Kövesi AB -

A novel correspondence-less approach is proposed to find a non-linear aligning transformation between a pair of deformable 3D objects. Herein, we consider a polynomial deformation model, but our framework can be easily adapted to other common deformations. The basic idea of the proposed method is to set up a system of nonlinear equations whose solution directly provides the parameters of the aligning transformation. Each equation is generated by integrating a nonlinear function over the object's domains. Thus the number of equations is determined by the number of adopted nonlinear functions yielding a flexible mechanism to generate sufficiently many equations. While classical approaches would establish correspondences between the shapes, our method works without landmarks. The efficiency of the proposed approach has been demonstrated on a large synthetic dataset as well as in the context of medical image registration.

JF - Proceedings of International Conference on Digital Image Computing: Techniques and Applications (DICTA) PB - IEEE CY - New York UR - http://www.inf.u-szeged.hu/~kato/papers/dicta2012.pdf N1 - UT: 000316318400010doi: 10.1109/DICTA.2012.6411674 ER - TY - CHAP T1 - Evaluation of Point Matching Methods for Wide-baseline Stereo Correspondence on Mobile Platforms T2 - Proceedings of the International Symposium on Image and Signal Processing and Analysis (ISPA) Y1 - 2013 A1 - Endre Juhász A1 - Attila Tanacs A1 - Zoltan Kato ED - Giovanni Ramponi ED - Sven Lončarić ED - Alberto Carini ED - Karen Egiazarian AB -

Wide-baseline stereo matching is a common problem of computer vision. By the explosion of smartphones equipped with camera modules, many classical computer vision solutions have been adapted to such platforms. Considering the widespread use of various networking options for mobile phones, one can consider a set of smart phones as an ad-hoc camera network, where each camera is equipped with a more and more powerful computing engine in addition to a limited bandwidth communication with other devices. Therefore the performance of classical vision algorithms in a collaborative mobile environment is of particular interest. In such a scenario we expect that the images are taken almost simultaneously but from different viewpoints, implying that the camera poses are significantly different but lighting conditions are the same. In this work, we provide quantitative comparison of the most important keypoint detectors and descriptors in the context of wide baseline stereo matching. We found that for resolution of 2 megapixels images the current mobile hardware is capable of providing results efficiently.

 

JF - Proceedings of the International Symposium on Image and Signal Processing and Analysis (ISPA) PB - IEEE CY - Trieste ER - TY - CHAP T1 - Linear and nonlinear shape alignment without correspondences T2 - Proceedings of International Joint Conference on Computer Vision, Imaging and Computer Graphics - Theory and Applications (Revised Selected Papers) Y1 - 2013 A1 - Zoltan Kato ED - Paul Richard ED - Gabriela Csurka AB -

We consider the estimation of diffeomorphic deformations aligning a known binary shape and its distorted observation. The classical solution consists in extracting landmarks, establishing correspondences and then the aligning transformation is obtained via a complex optimization procedure. Herein we present an alternative solution which works without landmark correspondences, is independent of the magnitude of transformation, easy to implement, and has a linear time complexity. The proposed universal framework is capable of recovering linear as well as nonlinear deformations.

 

JF - Proceedings of International Joint Conference on Computer Vision, Imaging and Computer Graphics - Theory and Applications (Revised Selected Papers) T3 - Communications in Computer and Information Science PB - Springer Verlag CY - Berlin; Heidelberg; New York; London; Paris; Tokyo UR - http://www.inf.u-szeged.hu/~kato/papers/visapp2012.pdf ER - TY - CHAP T1 - Pose Estimation of Ad-hoc Mobile Camera Networks T2 - International Conference on Digital Image Computing: Techniques and Applications (DICTA) Y1 - 2013 A1 - Zsolt Santa A1 - Zoltan Kato ED - Paulo de Souza ED - Ulrich Engelke ED - Ashfaqur Rahman AB -

An algorithm is proposed for the pose estimation of ad-hoc mobile camera networks with overlapping views. The main challenge is to estimate camera parameters with respect to the 3D scene without any specific calibration pattern, hence allowing for a consistent, camera-independent world coordinate system. The only assumption about the scene is that it contains a planar surface patch of a low-rank texture, which is visible in at least two cameras. Such low-rank patterns are quite common in urban environments. The proposed algorithm consists of three main steps: relative pose estimation of the cameras within the network, followed by the localization of the network within the 3D scene using a low-rank surface patch, and finally the estimation of a consistent scale for the whole system. The algorithm follows a distributed architecture, hence the computing power of the participating mobile devices are efficiently used. The performance and robustness of the proposed algorithm have been analyzed on both synthetic and real data. Experimental results confirmed the relevance and applicability of the method.

 

JF - International Conference on Digital Image Computing: Techniques and Applications (DICTA) PB - IEEE CY - Hobart, TAS ER - TY - CHAP T1 - Targetless Calibration of a Lidar - Perspective Camera Pair T2 - Proceedings of ICCV Workshop on Big Data in 3D Computer Vision Y1 - 2013 A1 - Tamás Levente A1 - Zoltan Kato ED - Jian Zhang ED - Mohammed Bennamoun ED - Dan Schonfeld ED - Zhengyou Zhang AB -

A novel method is proposed for the calibration of a camera - 3D lidar pair without the use of any special calibration pattern or point correspondences. The proposed method has no specific assumption about the data source: plain depth information is expected from the lidar scan and a simple perspective camera is used for the 2D images. The calibration is solved as a 2D-3D registration problem using a minimum of one (for extrinsic) or two (for intrinsic-extrinsic) planar regions visible in both cameras. The registration is then traced back to the solution of a non-linear system of equations which directly provides the calibration parameters between the bases of the two sensors. The method has been tested on a large set of synthetic lidar-camera image pairs as well as on real data acquired in outdoor environment.

 

JF - Proceedings of ICCV Workshop on Big Data in 3D Computer Vision PB - IEEE CY - Sydney, NSW N1 - doi: 10.1109/ICCVW.2013.92 ER - TY - CHAP T1 - A unifying framework for correspondence-less shape alignment and its medical applications T2 - Intelligent Interactive Technologies and Multimedia Y1 - 2013 A1 - Zoltan Kato AB -

We give an overview of our general framework for registering 2D and 3D objects without correspondences. Classical solutions consist in extracting landmarks, establishing correspondences and then the aligning transformation is obtained via a complex optimization procedure. In contrast, our framework works without landmark correspondences, is independent of the magnitude of transformation, easy to implement, and has a linear time complexity. The efficiency and robustness of the method has been demonstarted using various deformations models. Herein, we will focus on medical applications. © 2013 Springer-Verlag.

JF - Intelligent Interactive Technologies and Multimedia T3 - Communications in Computer and Information Science PB - Springer CY - Allahabad, India VL - 276 CCIS SN - 1865-0929 N1 - ScopusID: 84875170012doi: 10.1007/978-3-642-37463-0_4T3 2nd International Conference on Intelligent Interactive Technologies and Multimedia, IITM 2013Y2 9 March 2013 through 11 March 2013 CY Allahabad JO - COMMUN COMPUT INFORM SCI ER - TY - COMP T1 - Affine Registration of 3D Objects Y1 - 2012 AB -

This is the sample implementation and benchmark dataset of the binary image registration algorithm described in the following papers: Attila Tanacs and Zoltan Kato. Fast Linear Registration of 3D Objects Segmented from Medical Images. In Proceedings of International Conference on BioMedical Engineering and Informatics, Shanghai, China, pages 299--303, October 2011. IEEE. Attila Tanacs, Joakim Lindblad, Natasa Sladoje and Zoltan Kato. Estimation of Linear Deformations of 3D Objects. In Proceedings of International Conference on Image Processing, Hong Kong, China, pp. 153-156, September 2010. IEEE.

UR - http://www.inf.u-szeged.hu/~kato/software/affbin3dregdemo.html ER - TY - BOOK T1 - Markov random fields in image segmentation Y1 - 2012 A1 - Zoltan Kato A1 - Josiane Zerubia AB -

Markov Random Fields in Image Segmentation introduces the fundamentals of Markovian modeling in image segmentation as well as providing a brief overview of recent advances in the field.

PB - Now Publishers CY - Hanover, NH N1 - doi: 10.1561/2000000035 ER - TY - CONF T1 - A Multi-Layer Phase Field Model for Extracting Multiple Near-Circular Objects T2 - International Conference on Pattern Recognition (ICPR) Y1 - 2012 A1 - Csaba Molnar A1 - Zoltan Kato A1 - Ian Jermyn ED - Jan-Olof Eklundh ED - Yuichi Ohta ED - Steven Tanimoto AB -

This paper proposes a functional that assigns low `energy' to sets of subsets of the image domain consisting of a number of possibly overlapping near-circular regions of approximately a given radius: a `gas of circles'. The model can be used as a prior for object extraction whenever the objects conform to the `gas of circles' geometry, e.g. cells in biological images. Configurations are represented by a multi-layer phase field. Each layer has an associated function, regions being defined by thresholding. Intra-layer interactions assign low energy to configurations consisting of non-overlapping near-circular regions, while overlapping regions are represented in separate layers. Inter-layer interactions penalize overlaps. Here we present a theoretical and experimental analysis of the model.

 

JF - International Conference on Pattern Recognition (ICPR) PB - IEEE CY - Tsukuba, Japan SN - 978-1-4673-2216-4 ER - TY - JOUR T1 - Nonlinear Shape Registration without Correspondences JF - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Y1 - 2012 A1 - Csaba Domokos A1 - Jozsef Nemeth A1 - Zoltan Kato AB -

In this paper, we propose a novel framework to estimate the parameters of a diffeomorphism that aligns a known shape and its distorted observation. Classical registration methods first establish correspondences between the shapes and then compute the transformation parameters from these landmarks. Herein, we trace back the problem to the solution of a system of nonlinear equations which directly gives the parameters of the aligning transformation. The proposed method provides a generic framework to recover any diffeomorphic deformation without established correspondences. It is easy to implement, not sensitive to the strength of the deformation, and robust against segmentation errors. The method has been applied to several commonly used transformation models. The performance of the proposed framework has been demonstrated on large synthetic data sets as well as in the context of various applications.

 

PB - IEEE VL - 34 SN - 0162-8828 UR - http://www.inf.u-szeged.hu/~kato/papers/TPAMI-2010-03-0146.R2_Kato.pdf IS - 5 N1 - UT: 000301747400009doi: 10.1109/TPAMI.2011.200 JO - IEEE T PATTERN ANAL ER - TY - CHAP T1 - Parametric Stochastic Modeling for Color Image Segmentation and Texture Characterization T2 - Advanced color image processing and analysis Y1 - 2012 A1 - Imtnan-Ul-Haque Qazi A1 - Oliver Alata A1 - Zoltan Kato ED - Christine Fernandez-Maloigne AB -

Black should be made a color of light Clemence Boulouque

Parametric stochastic models offer the definition of color and/or texture features based on model parameters, which is of interest for color texture classification, segmentation and synthesis.

In this chapter, distribution of colors in the images through various parametric approximations including multivariate Gaussian distribution, multivariate Gaussian mixture models (MGMM) and Wishart distribution, is discussed. In the context of Bayesian color image segmentation, various aspects of sampling from the posterior distributions to estimate the color distribution from MGMM and the label field, using different move types are also discussed. These include reversible jump mechanism from MCMC methodology. Experimental results on color images are presented and discussed.

Then, we give some materials for the description of color spatial structure using Markov Random Fields (MRF), and more particularly multichannel GMRF, and multichannel linear prediction models. In this last approach, two dimensional complex multichannel versions of both causal and non-causal models are discussed to perform the simultaneous parametric power spectrum estimation of the luminance and the chrominance channels of the color image. Application of these models to the classification and segmentation of color texture images is also illustrated.

 

JF - Advanced color image processing and analysis PB - Springer CY - Berlin; Heidelberg; New York; London; Paris; Tokyo SN - 978-1-4419-6189-1 ER - TY - CONF T1 - Simultaneous Affine Registration of Multiple Shapes T2 - International Conference on Pattern Recognition (ICPR) Y1 - 2012 A1 - Csaba Domokos A1 - Zoltan Kato ED - Jan-Olof Eklundh ED - Yuichi Ohta ED - Steven Tanimoto AB -

The problem of simultaneously estimating affine deformations between multiple objects occur in many applications. Herein, a direct method is proposed which provides the result as a solution of a linear system of equations without establishing correspondences between the objects. The key idea is to construct enough linearly independent equations using covariant functions, and then finding the solution simultaneously for all affine transformations. Quantitative evaluation confirms the performance of the method.

 

JF - International Conference on Pattern Recognition (ICPR) PB - IEEE CY - Tsukuba, Japan SN - 978-1-4673-2216-4 ER - TY - CONF T1 - Spectral clustering to model deformations for fast multimodal prostate registration T2 - International Conference on Pattern Recognition (ICPR) Y1 - 2012 A1 - Jhimli Mitra A1 - Zoltan Kato A1 - Soumya Ghose A1 - Desire Sidibe A1 - Robert Martí A1 - Xavier Lladó A1 - Oliver Arnau A1 - Joan C Vilanova A1 - Fabrice Meriaudeau ED - Jan-Olof Eklundh ED - Yuichi Ohta ED - Steven Tanimoto AB -

This paper proposes a method to learn deformation parameters off-line for fast multimodal registration of ultrasound and magnetic resonance prostate images during ultrasound guided needle biopsy. The registration method involves spectral clustering of the deformation parameters obtained from a spline-based nonlinear diffeomorphism between training magnetic resonance and ultrasound prostate images. The deformation models built from the principal eigen-modes of the clusters are then applied on a test magnetic resonance image to register with the test ultrasound prostate image. The deformation model with the least registration error is finally chosen as the optimal model for deformable registration. The rationale behind modeling deformations is to achieve fast multimodal registration of prostate images while maintaining registration accuracies which is otherwise computationally expensive. The method is validated for 25 patients each with a pair of corresponding magnetic resonance and ultrasound images in a leave-one-out validation framework. The average registration accuracies i.e. Dice similarity coefficient of 0.927 ± 0.025, 95% Hausdorff distance of 5.14 ± 3.67 mm and target registration error of 2.44 ± 1.17 mm are obtained by our method with a speed-up in computation time by 98% when compared to Mitra et al. [7].

 

JF - International Conference on Pattern Recognition (ICPR) PB - IEEE CY - Tsukuba, Japan SN - 978-1-4673-2216-4 UR - http://hal.archives-ouvertes.fr/docs/00/71/09/43/PDF/ICPR_Jhimli.pdf ER - TY - JOUR T1 - A spline-based non-linear diffeomorphism for multimodal prostate registration. JF - MEDICAL IMAGE ANALYSIS Y1 - 2012 A1 - Jhimli Mitra A1 - Zoltan Kato A1 - Robert Martí A1 - Oliver Arnau A1 - Xavier Lladó A1 - Desire Sidibe A1 - Soumya Ghose A1 - Joan C Vilanova A1 - Josep Comet A1 - Fabrice Meriaudeau AB -

This paper presents a novel method for non-rigid registration of transrectal ultrasound and magnetic resonance prostate images based on a non-linear regularized framework of point correspondences obtained from a statistical measure of shape-contexts. The segmented prostate shapes are represented by shape-contexts and the Bhattacharyya distance between the shape representations is used to find the point correspondences between the 2D fixed and moving images. The registration method involves parametric estimation of the non-linear diffeomorphism between the multimodal images and has its basis in solving a set of non-linear equations of thin-plate splines. The solution is obtained as the least-squares solution of an over-determined system of non-linear equations constructed by integrating a set of non-linear functions over the fixed and moving images. However, this may not result in clinically acceptable transformations of the anatomical targets. Therefore, the regularized bending energy of the thin-plate splines along with the localization error of established correspondences should be included in the system of equations. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate mid-gland ultrasound and magnetic resonance images. The results obtained in terms of Dice similarity coefficient show an average of 0.980+/-0.004, average 95% Hausdorff distance of 1.63+/-0.48mm and mean target registration and target localization errors of 1.60+/-1.17mm and 0.15+/-0.12mm respectively.

VL - 16 SN - 1361-8415 IS - 6 N1 - UT: 000309694100015ScopusID: 84866118888doi: 10.1016/j.media.2012.04.006 JO - MED IMAGE ANAL ER - TY - CHAP T1 - A Unifying Framework for Correspondence-less Linear Shape Alignment T2 - International Conference on Image Analysis and Recognition (ICIAR) Y1 - 2012 A1 - Zoltan Kato ED - Aurélio Campilho AB -

We consider the estimation of linear transformations aligning a known binary shape and its distorted observation. The classical way to solve this registration problem is to find correspondences between the two images and then compute the transformation parameters from these landmarks. Here we propose a unified framework where the exact transformation is obtained as the solution of either a polynomial or a linear system of equations without establishing correspondences. The advantages of the proposed solutions are that they are fast, easy to implement, have linear time complexity, work without landmark correspondences and are independent of the magnitude of transformation.

 

JF - International Conference on Image Analysis and Recognition (ICIAR) T3 - Lecture Notes in Computer Science PB - Springer Verlag CY - Aveiro, Portugal SN - 978-3-642-31294-6 N1 - UT: 000323558000033 JO - LNCS ER - TY - CONF T1 - A Unifying Framework for Non-linear Registration of 3D Objects T2 - IEEE International Conference on Cognitive Infocommunications (CogInfoCom) Y1 - 2012 A1 - Zsolt Santa A1 - Zoltan Kato AB -

An extension of our earlier work is proposed to find a non-linear aligning transformation between a pair of deformable 3D objects. The basic idea is to set up a system of nonlinear equations whose solution directly provides the parameters of the aligning transformation. Each equation is generated by integrating a nonlinear function over the object's domains. Thus the number of equations is determined by the number of adopted nonlinear functions yielding a flexible mechanism to generate sufficiently many equations. While classical approaches would establish correspondences between the shapes, our method works without landmarks. Experiments with 3D polynomial and thin plate spline deformations confirm the performance of the framework.

 

JF - IEEE International Conference on Cognitive Infocommunications (CogInfoCom) PB - IEEE CY - Kosice, Slovakia SN - 978-1-4673-5187-4 UR - http://www.inf.u-szeged.hu/~kato/papers/coginfocomm2012.pdf N1 - UT: 000320454200086 ER - TY - CONF T1 - 3D objektumok lineáris deformációinak becslése T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - Attila Tanacs A1 - Joakim Lindblad A1 - Nataša Sladoje A1 - Zoltan Kato ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged ER - TY - CONF T1 - Affin Puzzle: Deformált objektumdarabok helyreállítása megfeleltetések nélkül T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - Csaba Domokos A1 - Zoltan Kato ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged UR - http://www.inf.u-szeged.hu/kepaf2011/pdfs/S05_03.pdf N1 - Kuba Attila Díjas cikk. ER - TY - CONF T1 - Bináris tomográfiai rekonstrukció objektum alapú evolúciós algoritmussal T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged ER - TY - CONF T1 - Élősejt szegmentálása gráfvágás segítségével fluoreszcenciás mikroszkóp képeken T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - Milan Lesko A1 - Zoltan Kato A1 - Antal Nagy A1 - Imre Gombos A1 - Zsolt Török A1 - László Vígh A1 - László Vígh ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged UR - http://www.inf.u-szeged.hu/kepaf2011/pdfs/S08_02.pdf ER - TY - CONF T1 - Fast linear registration of 3D objects segmented from medical images T2 - Biomedical Engineering and Informatics (BMEI) Y1 - 2011 A1 - Attila Tanacs A1 - Zoltan Kato ED - Yongsheng Ding ED - Yonghong Peng ED - Riyi Shi ED - Kuangrong Hao ED - Lipo Wang AB -

In this paper a linear registration framework is used for medical image registration using segmented binary objects. The method is best suited for problems where the segmentation is available, but we also propose a general bone segmentation approach for CT images. We focus on the case when the objects to be registered differ considerably because of segmentation errors. We check the applicability of the method to bone segmentation of pelvic and thoracic CT images. Comparison is also made against a classical mutual information-based registration method. © 2011 IEEE.

JF - Biomedical Engineering and Informatics (BMEI) PB - IEEE CY - Shanghai SN - 978-1-4244-9351-7 N1 - ScopusID: 84855764850doi: 10.1109/BMEI.2011.6098290 ER - TY - CONF T1 - Iterációnkénti simítással kombinált vékonyítás T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - Péter Kardos A1 - Gábor Németh A1 - Kálmán Palágyi ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged UR - http://www.inf.u-szeged.hu/kepaf2011/pdfs/S05_01.pdf ER - TY - CONF T1 - Mediánszűrés alkalmazása algebrai rekonstrukciós módszerekben T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - Norbert Hantos A1 - Péter Balázs ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged ER - TY - CHAP T1 - A Multi-Layer 'Gas of Circles' Markov Random Field Model for the Extraction of Overlapping Near-Circular Objects T2 - Advances Concepts for Intelligent Vision Systems (ACIVS) Y1 - 2011 AB -

We propose a multi-layer binary Markov random field (MRF) model that assigns high probability to object configurations in the image domain consisting of an unknown number of possibly touching or overlapping near-circular objects of approximately a given size. Each layer has an associated binary field that specifies a region corresponding to objects. Overlapping objects are represented by regions in different layers. Within each layer, long-range interactions favor connected components of approximately circular shape, while regions in different layers that overlap are penalized. Used as a prior coupled with a suitable data likelihood, the model can be used for object extraction from images, e.g. cells in biological images or densely-packed tree crowns in remote sensing images. We present a theoretical and experimental analysis of the model, and demonstrate its performance on various synthetic and biomedical images.

JF - Advances Concepts for Intelligent Vision Systems (ACIVS) T3 - Lecture Notes in Computer Science PB - Springer-Verlag CY - Ghent, Belgium SN - 978-3-642-23686-0 UR - http://www.inf.u-szeged.hu/ipcg/publications/Year/2011.complete.xml#Nemeth-etal2011 N1 - UT: 000306962700016 JO - LNCS ER - TY - CONF T1 - A non-linear diffeomorphic framework for prostate multimodal registration T2 - International Conference on Digital Image Computing: Techniques and Applications (DICTA) Y1 - 2011 A1 - Jhimli Mitra A1 - Zoltan Kato A1 - Robert Martí A1 - Oliver Arnau A1 - Xavier Lladó A1 - Soumya Ghose A1 - Joan C Vilanova A1 - Fabrice Meriaudeau AB -

This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thinplate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate midgland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95% Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively. © 2011 IEEE.

JF - International Conference on Digital Image Computing: Techniques and Applications (DICTA) PB - IEEE CY - Noosa, QLD SN - 978-1-4577-2006-2 N1 - ScopusID: 84856980939doi: 10.1109/DICTA.2011.14 ER - TY - COMP T1 - Nonlinear Shape Registration without Correspondences Y1 - 2011 A1 - Zoltán Kornél Török A1 - Csaba Domokos A1 - Jozsef Nemeth A1 - Zoltan Kato AB -

This is the sample implementation and benchmark dataset of the nonlinear registration of 2D shapes described in the following papers: Csaba Domokos, Jozsef Nemeth, and Zoltan Kato. Nonlinear Shape Registration without Correspondences. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(5):943--958, May 2012. Note that the current demo program implements only planar homography deformations. Other deformations can be easily implemented based on the demo code.

UR - http://www.inf.u-szeged.hu/~kato/software/planarhombinregdemo.html ER - TY - BOOK T1 - Számítógépes látás Y1 - 2011 A1 - Zoltan Kato A1 - László Czúni PB - Typotex Kiadó CY - Budapest ER - TY - CONF T1 - A topológia-megőrzés elegendő feltételein alapuló 3D párhuzamos vékonyító algoritmusok T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - Gábor Németh A1 - Péter Kardos A1 - Kálmán Palágyi ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged UR - http://www.inf.u-szeged.hu/kepaf2011/pdfs/S05_02.pdf ER - TY - CONF T1 - Vetületi irányfüggőség a bináris tomográfiában T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 Y1 - 2011 A1 - László Gábor Varga A1 - Péter Balázs A1 - Antal Nagy ED - Zoltan Kato ED - Kálmán Palágyi JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2011 PB - NJSZT CY - Szeged ER - TY - CHAP T1 - Affine puzzle: Realigning deformed object fragments without correspondences T2 - European Conference on Computer Vision (ECCV) Y1 - 2010 A1 - Csaba Domokos A1 - Zoltan Kato ED - Kostas Daniilidis ED - Petros Maragos ED - Nikos Paragios AB -

This paper is addressing the problem of realigning broken objects without correspondences. We consider linear transformations between the object fragments and present the method through 2D and 3D affine transformations. The basic idea is to construct and solve a polynomial system of equations which provides the unknown parameters of the alignment. We have quantitatively evaluated the proposed algorithm on a large synthetic dataset containing 2D and 3D images. The results show that the method performs well and robust against segmentation errors. We also present experiments on 2D real images as well as on volumetric medical images applied to surgical planning. © 2010 Springer-Verlag.

JF - European Conference on Computer Vision (ECCV) T3 - Lecture Notes in Computer Science PB - Springer CY - Crete, Greece SN - 978-3-642-15551-2 N1 - UT: 000286164000056ScopusID: 78149337447doi: 10.1007/978-3-642-15552-9_56 JO - LNCS ER - TY - CHAP T1 - Estimation of linear deformations of 3D objects T2 - IEEE International Conference on Image Processing (ICIP) Y1 - 2010 A1 - Attila Tanacs A1 - Joakim Lindblad A1 - Nataša Sladoje A1 - Zoltan Kato AB -

We propose a registration method to find affine transformations between 3D objects by constructing and solving an overdetermined system of polynomial equations. We utilize voxel coverage information for more precise object boundary description. An iterative solution enables us to easily adjust the method to recover e.g. rigid-body and similarity transformations. Synthetic tests show the advantage of the voxel coverage representation, and reveal the robustness properties of our method against different types of segmentation errors. The method is tested on a real medical CT volume. © 2010 IEEE.

JF - IEEE International Conference on Image Processing (ICIP) PB - IEEE CY - Hong Kong, Hong Kong N1 - UT: 000287728000038ScopusID: 78651064516doi: 10.1109/ICIP.2010.5650932 ER - TY - CHAP T1 - Live cell segmentation in fluorescence microscopy via graph cut T2 - 20th international conference on pattern recognition (ICPR 2010) Y1 - 2010 A1 - Milan Lesko A1 - Zoltan Kato A1 - Antal Nagy A1 - Imre Gombos A1 - Zsolt Török A1 - László Vígh A1 - László Vígh ED - Aytul Ercil AB -

We propose a novel Markovian segmentation model which takes into account edge information. By construction, the model uses only pairwise interactions and its energy is submodular. Thus the exact energy minima is obtained via a max-flow/min-cut algorithm. The method has been quantitatively evaluated on synthetic images as well as on fluorescence microscopic images of live cells. © 2010 IEEE.

JF - 20th international conference on pattern recognition (ICPR 2010) PB - IEEE CY - Istanbul, Turkey SN - 978-1-4244-7542-1 N1 - ScopusID: 78149486419doi: 10.1109/ICPR.2010.367Besorolás: Konferenciaközlemény ER - TY - JOUR T1 - Parametric estimation of affine deformations of planar shapes JF - PATTERN RECOGNITION Y1 - 2010 A1 - Csaba Domokos A1 - Zoltan Kato VL - 43 SN - 0031-3203 IS - 3 N1 - UT: 000273094100003doi: 10.1016/j.patcog.2009.08.013 JO - PATTERN RECOGN ER - TY - CHAP T1 - SITIS 2010: Track SIT editorial message: Signal and Image Technologies T2 - Proceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010 Y1 - 2010 A1 - Albert Dipanda A1 - Zoltan Kato ED - Albert Dipanda ED - Richard Chbeir ED - Kokou Yetongnon JF - Proceedings of the 6th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2010 PB - IEEE Computer Society Press CY - Kuala Lumpur N1 - ScopusID: 79952549721 ER - TY - CHAP T1 - Affine alignment of compound objects: A direct approach T2 - 16th IEEE International Conference on Image Processing (ICIP), 2009 Y1 - 2009 A1 - Csaba Domokos A1 - Zoltan Kato AB -

A direct approach for parametric estimation of 2D affine deformations between compound shapes is proposed. It provides the result as a least-square solution of a linear system of equations. The basic idea is to fit Gaussian densities over the objects yielding covariant functions, which preserves the effect of the unknown transformation. Based on these functions, linear equations are constructed by integrating nonlinear functions over appropriate domains. The main advantages are: linear complexity, easy implementation, works without any time consuming optimization or established correspondences. Comparative tests show that it outperforms state-of-the-art methods both in terms of precision, robustness and complexity. ©2009 IEEE.

JF - 16th IEEE International Conference on Image Processing (ICIP), 2009 PB - IEEE CY - Cairo, Egypt SN - 978-1-4244-5653-6 N1 - UT: 000280464300043ScopusID: 77951939917doi: 10.1109/ICIP.2009.5414195 ER - TY - COMP T1 - Affine Registration of Planar Shapes Y1 - 2009 A1 - Zsolt Katona A1 - Csaba Domokos A1 - Zoltan Kato AB -

This is the sample implementation and benchmark dataset of the binary image registration algorithm described in the following paper: Csaba Domokos and Zoltan Kato. Parametric Estimation of Affine Deformations of Planar Shapes. Pattern Recognition, 43(3):569--578, March 2010.

UR - http://www.inf.u-szeged.hu/~kato/software/affbinregdemo.html ER - TY - JOUR T1 - Detection of Object Motion Regions in Aerial Image Pairs with a Multilayer Markovian Model JF - IEEE TRANSACTIONS ON IMAGE PROCESSING Y1 - 2009 A1 - Csaba Benedek A1 - Tamas Sziranyi A1 - Zoltan Kato A1 - Josiane Zerubia AB -

We propose a new Bayesian method for detectingthe regions of object displacements in aerial image pairs. We use a robust but coarse 2-D image registration algorithm. Our main challenge is to eliminate the registration errors from the extracted change map. We introduce a three-layer Markov Random Field (L3MRF) model which integrates information from two different features, and ensures connected homogenous regions in the segmented images. Validation is given on real aerial photos.

PB - IEEE VL - 18 SN - 1057-7149 IS - 10 N1 - UT: 000269715500013ScopusID: 70349442338doi: 10.1109/TIP.2009.2025808 JO - IEEE T IMAGE PROCESS ER - TY - JOUR T1 - A higher-order active contour model of a 'gas of circles' and its application to tree crown extraction JF - PATTERN RECOGNITION Y1 - 2009 A1 - Peter Horvath A1 - Ian Jermyn A1 - Zoltan Kato A1 - Josiane Zerubia VL - 42 SN - 0031-3203 IS - 5 N1 - UT: 000263431200011doi: 10.1016/j.patcog.2008.09.008 JO - PATTERN RECOGN ER - TY - CONF T1 - Kör alakú objektumok szegmentálása Markov mező segítségével T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 Y1 - 2009 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 PB - Akaprint CY - Budapest UR - http://vision.sztaki.hu/~kepaf/kepaf2009_CD/files/116-4-MRFCircle08.pdf N1 - Received the Attila Kuba Prize ER - TY - CHAP T1 - A Markov random field model for extracting near-circular shapes T2 - 16th IEEE International Conference on Image Processing (ICIP) Y1 - 2009 A1 - Tamás Blaskovics A1 - Zoltan Kato A1 - Ian Jermyn AB -

We propose a binary Markov Random Field (MRF) model that assigns high probability to regions in the image domain consisting of an unknown number of circles of a given radius. We construct the model by discretizing the 'gas of circles' phase field model in a principled way, thereby creating an 'equivalent'MRF. The behaviour of the resultingMRF model is analyzed, and the performance of the new model is demonstrated on various synthetic images as well as on the problem of tree crown detection in aerial images. ©2009 IEEE.

JF - 16th IEEE International Conference on Image Processing (ICIP) PB - IEEE CY - Cairo, Egypt SN - 978-1-4244-5653-6 N1 - UT: 000280464300268ScopusID: 77951945383doi: 10.1109/ICIP.2009.5413472 ER - TY - CONF T1 - Nonlinear registration of binary shapes T2 - 16th IEEE International Conference on Image Processing (ICIP) Y1 - 2009 A1 - Jozsef Nemeth A1 - Csaba Domokos A1 - Zoltan Kato AB -

A novel approach is proposed to estimate the parameters of a diffeomorphism that aligns two binary images. Classical approaches usually define a cost function based on a similarity metric and then find the solution via optimization. Herein, we trace back the problem to the solution of a system of non-linear equations which directly provides the parameters of the aligning transformation. The proposed method works without any time consuming optimization step or established correspondences. The advantage of our algorithm is that it is easy to implement, less sensitive to the strength of the deformation, and robust against segmentation errors. The efficiency of the proposed approach has been demonstrated on a large synthetic dataset as well as in the context of an industrial application. ©2009 IEEE.

JF - 16th IEEE International Conference on Image Processing (ICIP) PB - IEEE CY - Cairo, Egypt SN - 978-1-4244-5653-6 N1 - UT: 000280464300275ScopusID: 77951946286doi: 10.1109/ICIP.2009.5413468 ER - TY - CHAP T1 - Recovering affine deformations of fuzzy shapes T2 - Image Analysis Y1 - 2009 A1 - Attila Tanacs A1 - Csaba Domokos A1 - Nataša Sladoje A1 - Joakim Lindblad A1 - Zoltan Kato ED - Arnt-Borre Salberg ED - Jon Yngve Hardeberg ED - Robert Jenssen AB -

Fuzzy sets and fuzzy techniques are attracting increasing attention nowadays in the field of image processing and analysis. It has been shown that the information preserved by using fuzzy representation based on area coverage may be successfully utilized to improve precision and accuracy of several shape descriptors; geometric moments of a shape are among them. We propose to extend an existing binary shape matching method to take advantage of fuzzy object representation. The result of a synthetic test show that fuzzy representation yields smaller registration errors in average. A segmentation method is also presented to generate fuzzy segmentations of real images. The applicability of the proposed methods is demonstrated on real X-ray images of hip replacement implants. © 2009 Springer Berlin Heidelberg.

JF - Image Analysis T3 - Lecture Notes in Computer Science PB - Springer-Verlag CY - Oslo, Norway N1 - UT: 000268661000075ScopusID: 70350676212doi: 10.1007/978-3-642-02230-2_75 JO - LNCS ER - TY - CHAP T1 - Recovering planar homographies between 2D shapes T2 - 12th International Conference on Computer Vision, ICCV 2009 Y1 - 2009 AB -

Images taken from different views of a planar object are related by planar homography. Recovering the parameters of such transformations is a fundamental problem in computer vision with various applications. This paper proposes a novel method to estimate the parameters of a homography that aligns two binary images. It is obtained by solving a system of nonlinear equations generated by integrating linearly independent functions over the domains determined by the shapes. The advantage of the proposed solution is that it is easy to implement, less sensitive to the strength of the deformation, works without established correspondences and robust against segmentation errors. The method has been tested on synthetic as well as on real images and its efficiency has been demonstrated in the context of two different applications: alignment of hip prosthesis X-ray images and matching of traffic signs. ©2009 IEEE.

JF - 12th International Conference on Computer Vision, ICCV 2009 PB - IEEE N1 - UT: 000294955300280ScopusID: 77953177385doi: 10.1109/ICCV.2009.5459474 ER - TY - CONF T1 - Síkbeli alakzatok regisztrációja kovariáns függvények felhasználásával T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 Y1 - 2009 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 PB - Akaprint CY - Budapest ER - TY - CONF T1 - Síkhomográfia paramétereinek becslése bináris képeken T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 Y1 - 2009 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2009 PB - Akaprint CY - Budapest ER - TY - ABST T1 - Supervised Color Image Segmentation in a Markovian Framework Y1 - 2009 A1 - Mihály Gara A1 - Zoltan Kato AB -

This is the sample implementation of a Markov random field based color image segmentation algorithm described in the following paper: Zoltan Kato, Ting Chuen Pong, and John Chung Mong Lee. Color Image Segmentation and Parameter Estimation in a Markovian Framework. Pattern Recognition Letters, 22(3-4):309--321, March 2001. Note that the current demo program implements only a supervised version of the segmentation method described in the above paper (i.e. parameter values are learned interactively from representative regions selected by the user). Otherwise, the program implements exactly the color MRF model proposed in the paper. Images are automatically converted from RGB to the perceptually uniform CIE-L*u*v* color space before segmentation.

UR - http://www.inf.u-szeged.hu/~kato/software/colormrfdemo.html ER - TY - CHAP T1 - Binary image registration using covariant gaussian densities T2 - Image Analysis and Recognition Y1 - 2008 A1 - Csaba Domokos A1 - Zoltan Kato ED - Aurélio Campilho AB -

We consider the estimation of 2D affine transformations aligning a known binary shape and its distorted observation. The classical way to solve this registration problem is to find correspondences between the two images and then compute the transformation parameters from these landmarks. In this paper, we propose a novel approach where the exact transformation is obtained as a least-squares solution of a linear system. The basic idea is to fit a Gaussian density to the shapes which preserves the effect of the unknown transformation. It can also be regarded as a consistent coloring of the shapes yielding two rich functions defined over the two shapes to be matched. The advantage of the proposed solution is that it is fast, easy to implement, works without established correspondences and provides a unique and exact solution regardless of the magnitude of transformation. © 2008 Springer-Verlag Berlin Heidelberg.

JF - Image Analysis and Recognition T3 - Lecture Notes in Computer Science PB - Springer CY - Póvoa de Varzim, Portugal SN - 978-3-540-69811-1 N1 - UT: 000257302500045ScopusID: 47749098390doi: 10.1007/978-3-540-69812-8_45 JO - LNCS ER - TY - CHAP T1 - A képfeldolgozás kutatása a Szegedi Tudományegyetemen T2 - Informatika a felsőoktatásban 2008 Y1 - 2008 AB - 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. JF - Informatika a felsőoktatásban 2008 PB - Debreceni Egyetem Informatikai Kar CY - Debrecen UR - http://www.agr.unideb.hu/if2008/kiadvany/papers/E62.pdf N1 - Art. No.: E62 ER - TY - CHAP T1 - Parametric estimation of affine deformations of binary images T2 - Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Y1 - 2008 A1 - Csaba Domokos A1 - Zoltan Kato A1 - Joseph M Francos AB -

We consider the problem of planar object registration on binary images where the aligning transformation is restricted to the group of affine transformations. Previous approaches usually require established correspondences or the solution of nonlinear optimization problems. Herein we show that it is possible to formulate the problem as the solution of a system of up to third order polynomial equations. These equations are constructed in a simple way using some basic geometric information of binary images. It does not need established correspondences nor the solution of complex optimization problems. The resulting algorithm is fast and provides a direct solution regardless of the magnitude of transformation. ©2008 IEEE.

JF - Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) PB - IEEE CY - Las Vegas, NV, USA SN - 978-1-4244-1483-3 N1 - UT: 000257456700223ScopusID: 51449098982doi: 10.1109/ICASSP.2008.4517753 ER - TY - JOUR T1 - Segmentation of color images via reversible jump MCMC sampling JF - IMAGE AND VISION COMPUTING Y1 - 2008 A1 - Zoltan Kato PB - Elsevier VL - 26 SN - 0262-8856 IS - 3 N1 - UT: 000252196500005doi: 10.1016/j.imavis.2006.12.004 JO - IMAGE VISION COMPUT ER - TY - CONF T1 - Kör alakú objektumok szegmentálása magasabb rendű aktív kontúr modellek segítségével T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 Y1 - 2007 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 PB - Képfeldolgozók és Alakfelismerők Társasága CY - Debrecen ER - TY - THES T1 - Markovian Image Models and their Application in Image Segmentation Y1 - 2007 A1 - Zoltan Kato ER - TY - CONF T1 - Parametric Estimation of Two-Dimensional Affine Transformations of Binary Images T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 Y1 - 2007 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2007 PB - Képfeldolgozók és Alakfelismerők Társasága CY - Debrecen ER - TY - ABST T1 - A Three-layer MRF model for Object Motion Detection in Airborne Images Y1 - 2007 A1 - Csaba Benedek A1 - Tamas Sziranyi A1 - Zoltan Kato A1 - Josiane Zerubia ER - TY - CHAP T1 - A higher-order active contour model for tree detection T2 - Proceedings of the18th International Conference on Pattern Recognition, ICPR 2006 Y1 - 2006 AB -

We present a model of a 'gas of circles', the ensemble of regions in the image domain consisting of an unknown number of circles with approximately fixed radius and short range repulsive interactions, and apply it to the extraction of tree crowns from aerial images. The method uses the recently introduced 'higher order active contours' (HOACs), which incorporate long-range interactions between contour points, and thereby include prior geometric information without using a template shape. This makes them ideal when looking for multiple instances of an entity in an image. We study an existing HOAC model for networks, and show via a stability calculation that circles stable to perturbations are possible for constrained parameter sets. Combining this prior energy with a data term, we show results on aerial imagery that demonstrate the effectiveness of the method and the need for prior geometric knowledge. The model has many other potential applications. © 2006 IEEE.

JF - Proceedings of the18th International Conference on Pattern Recognition, ICPR 2006 PB - IEEE N1 - ScopusID: 34047219865doi: 10.1109/ICPR.2006.79 ER - TY - CONF T1 - A Higher-Order Active Contour Model for Tree Detection T2 - Proceedings of the International Conference on Pattern Recognition (ICPR) Y1 - 2006 A1 - Peter Horvath A1 - Ian Jermyn A1 - Zoltan Kato A1 - Josiane Zerubia AB -

We present a model of a 'gas of circles', the ensemble of regions in the image domain consisting of an unknown number of circles with approximately fixed radius and short range repulsive interactions, and apply it to the extraction of tree crowns from aerial images. The method uses the recently introduced 'higher order active contours' (HOACs), which incorporate long-range interactions between contour points, and thereby include prior geometric information without using a template shape. This makes them ideal when looking for multiple instances of an entity in an image. We study an existing HOAC model for networks, and show via a stability calculation that circles stable to perturbations are possible for constrained parameter sets. Combining this prior energy with a data term, we show results on aerial imagery that demonstrate the effectiveness of the method and the need for prior geometric knowledge. The model has many other potential applications.

JF - Proceedings of the International Conference on Pattern Recognition (ICPR) PB - IAPR CY - Hong Kong, China VL - 2 ER - TY - ABST T1 - A Higher-Order Active Contour Model of a `Gas of Circles' and its Application to Tree Crown Extraction Y1 - 2006 ER - TY - CHAP T1 - An Improved `Gas of Circles' Higher-Order Active Contour Model and its Application to Tree Crown Extraction T2 - Proceedings of Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) Y1 - 2006 JF - Proceedings of Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) PB - Springer Verlag CY - Berlin; Heidelberg; New York N1 - doi: 10.1007/11949619_14 ER - TY - JOUR T1 - A Markov random field image segmentation model for color textured images JF - IMAGE AND VISION COMPUTING Y1 - 2006 VL - 24 SN - 0262-8856 IS - 10 N1 - UT: 000241228300006doi: 10.1016/j.imavis.2006.03.005 JO - IMAGE VISION COMPUT ER - TY - CHAP T1 - A multi-layer MRF model for object-motion detection in unregistered airborne image-pairs T2 - Proceedings - 14th International Conference on Image Processing, ICIP 2007 Y1 - 2006 JF - Proceedings - 14th International Conference on Image Processing, ICIP 2007 PB - IEEE CY - Piscataway UR - http://www.icip2007.org/Papers/AcceptedList.asp ER - TY - CHAP T1 - A multi-layer MRF model for video object segmentation T2 - COMPUTER VISION - ACCV 2006, PT II Y1 - 2006 JF - COMPUTER VISION - ACCV 2006, PT II PB - Springer Verlag N1 - UT: 000235773200095doi: 10.1007/11612704_95 ER - TY - CHAP T1 - Shape Moments for Region Based Active Contours T2 - 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 Y1 - 2005 JF - 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 PB - OCG CY - Vienna ER - TY - ABST T1 - Supervised Image Segmentation Using Markov Random Fields Y1 - 2005 AB - This is the sample implementation of a Markov random field based image segmentation algorithm described in the following papers: Mark Berthod, Zoltan Kato, Shan Yu, and Josiane Zerubia. Bayesian Image Classification Using Markov Random Fields. Image and Vision Computing, 14:285--295, 1996. Keyword(s): Bayesian image classification, Markov random fields, Optimisation. Zoltan Kato, Josiane Zerubia, and Mark Berthod. Satellite Image Classification Using a Modified Metropolis Dynamics. In Proceedings of International Conference on Acoustics, Speech and Signal Processing, volume 3, San-Francisco, California, USA, pages 573-576, March 1992. IEEE. Zoltan Kato. Modélisations markoviennes multirésolutions en vision par ordinateur. Application a` la segmentation d'images SPOT. PhD Thesis, INRIA, Sophia Antipolis, France, December 1994. Note: Available in French (follow the URL link) and English. Keyword(s): computer vision, early vision, Markovian model, multiscale model, hierarchical model, parallel combinatorial optimization algorithm, multi-temperature annealing, parameter estimation. UR - http://www.inf.u-szeged.hu/~kato/software/mrfdemo.html ER - TY - CHAP T1 - Video Object Segmentation Using a Multicue Markovian Model T2 - 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 Y1 - 2005 JF - 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 PB - OCG CY - Vienna ER - TY - CONF T1 - Color, Texture and Motion Segmentation Using Gradient Vector Flow T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 Y1 - 2004 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 CY - Miskolctapolca ER - TY - CONF T1 - Color textured image segmentation using a multi-layer Markovian model T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 Y1 - 2004 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 CY - Miskolctapolca ER - TY - CONF T1 - Optical Flow Computation Using an Energy Minimization Approach T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 Y1 - 2004 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 CY - Miskolctapolca ER - TY - CONF T1 - Reversible Jump Markov Chain Monte Carlo for Unsupervised MRF Color Image SegmentationProceedings of Brithish Machine Vision Conference (BMVC) Y1 - 2004 PB - BMVA UR - http://www.bmva.org/bmvc/2004/papers/paper_223.pdf ER - TY - CONF T1 - Reversible Jump Markov Chain Monte Carlo for Unsupervised MRF Color Image Segmentation T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 Y1 - 2004 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 CY - Miskolctapolca ER - TY - CONF T1 - Számítógépes képfeldolgozás oktatása a Szegedi Tudományegyetemen T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 Y1 - 2004 AB -

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.

JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 2004 PB - Neumann János Számítógép-tudományi Társaság CY - Miskolc ER - TY - CHAP T1 - Non-Photorealistic Rendering and Content-Based Image Retrieval T2 - Proceedings of 11th Pacific Conference on Computer Graphics and Applications (PG) Y1 - 2003 JF - Proceedings of 11th Pacific Conference on Computer Graphics and Applications (PG) PB - IEEE Computer Soc. Pr. CY - New York N1 - doi: 10.1109/PCCGA.2003.1238257 ER - TY - CHAP T1 - Unsupervised segmentation of color textured images using a multi-layer MRF model T2 - ICIP 2003: IEEE International Conference on Image Processing Y1 - 2003 AB -

Herein, we propose a novel multi-layer Markov random field (MRF) image segmentation model which aims at combining color and texture features: Each feature is associated to a so called feature layer, where an MRF model is defined using only the corresponding feature. A special layer is assigned to the combined MRF model. This layer interacts with each feature layer and provides the segmentation based on the combination of different features. The model is quite generic and isn't restricted to a particular texture feature. Herein we will test the algorithm using Gabor and MRSAR texture features. Furthermore, the algorithm automatically estimates the number of classes at each layer (there can be different classes at different layers) and the associated model parameters.

JF - ICIP 2003: IEEE International Conference on Image Processing PB - IEEE N1 - ScopusID: 0344666539doi: 10.1109/ICIP.2003.1247124 ER - TY - CONF T1 - Content-based image retrieval using stochastic paintbrush transformation T2 - IEEE - International Conference on Image Processing: ICIP Y1 - 2002 JF - IEEE - International Conference on Image Processing: ICIP PB - IEEE Computer Society Press CY - Aix-en-Provence N1 - UT: 000185208200237 ER - TY - JOUR T1 - Markov random fields in image processing application to remote sensing and astrophysics JF - JOURNAL DE PHYSIQUE IV Y1 - 2002 VL - 12 SN - 1155-4339 IS - 1 N1 - UT: 000175261200006doi: 10.1051/jp42002005 JO - J PHYS IV ER - TY - CHAP T1 - Multicue MRF image segmentation: Combining texture and color features T2 - Proceedings 16th International Conference on Pattern Recognition (ICPR 2002) Y1 - 2002 AB -

Herein, we propose a new Markov random field (MRF) image segmentation model which aims at combining color and texture features. The model has a multi-layer structure: Each feature has its own layer, called feature layer, where an MRF model is defined using only the corresponding feature. A special layer is assigned to the combined MRF model. This layer interacts with each feature layer and provides the segmentation based on the combination of different features. The uniqueness of our algorithm is that it provides both color only and texture only segmentations as well as a segmentation based on combined color and texture features. The number of classes on feature layers is given by the user but it is estimated on the combined layer. © 2002 IEEE.

JF - Proceedings 16th International Conference on Pattern Recognition (ICPR 2002) PB - IEEE Computer Society N1 - ScopusID: 33751583776 ER - TY - JOUR T1 - Color image segmentation and parameter estimation in a markovian framework JF - PATTERN RECOGNITION LETTERS Y1 - 2001 AB -

An unsupervised color image segmentation algorithm is presented, using a Markov random field (MRF) pixel classification model. We propose a new method to estimate initial mean vectors effectively even if the histogram does not have clearly distinguishable peaks. The only parameter supplied by the user is the number of classes. © 2001 Elsevier Science B.V. All rights reserved.

VL - 22 SN - 0167-8655 IS - 3-4 N1 - UT: 000167983900005ScopusID: 0035272740doi: 10.1016/S0167-8655(00)00106-9 JO - PATTERN RECOGN LETT ER - TY - CHAP T1 - A Markov Random Field Image Segmentation Model Using Combined Color and Texture Features T2 - Proceedings of International Conference on Computer Analysis of Images and Patterns (CAIP) Y1 - 2001 JF - Proceedings of International Conference on Computer Analysis of Images and Patterns (CAIP) PB - Springer Verlag CY - Berlin; Heidelberg N1 - doi: 10.1007/3-540-44692-3_66 ER - TY - JOUR T1 - Image segmentation using Markov random field model in fully parallel cellular network architectures JF - REAL-TIME IMAGING Y1 - 2000 VL - 6 SN - 1077-2014 UR - http://www.sztaki.hu/~sziranyi/Papers/Sziranyi_MRF.pdf IS - 3 N1 - UT: 000088331700003ScopusID: 0034204755 JO - REAL-TIME IMAGING ER - TY - ABST T1 - Bayesian Color Image Segmentation Using Reversible Jump Markov Chain Monte Carlo Y1 - 1999 N1 - http://dl.acm.org/citation.cfm?id=869110http://dl.acm.org/citation.cfm?id=869110 ER - TY - RPRT T1 - Bayesian Color Image Segmentation Using Reversible Jump Markov Chain Monte Carlo Y1 - 1999 A1 - Zoltan Kato PB - ERCIM/CWI CY - Amsterdam, The Netherlands ER - TY - JOUR T1 - Unsupervised parallel image classification using Markovian models JF - PATTERN RECOGNITION Y1 - 1999 AB -

This paper deals with the problem of unsupervised classification of images modeled by Markov random fields (MRF). If the model parameters are known then we have various methods to solve the segmentation problem (simulated annealing (SA), iterated conditional modes (ICM), etc). However, when the parameters are unknown, the problem becomes more difficult. One has to estimate the hidden label field parameters only from the observed image. Herein, we are interested in parameter estimation methods related to monogrid and hierarchical MRF models. The basic idea is similar to the expectation-maximization (EM) algorithm: we recursively look at the maximum a posteriori (MAP) estimate of the label field given the estimated parameters, then we look at the maximum likelihood (ML) estimate of the parameters given a tentative labeling obtained at the previous step. The only parameter supposed to be known is the number of classes, all the other parameters are estimated. The proposed algorithms have been implemented on a Connection Machine CM200. Comparative experiments have been performed on both noisy synthetic data and real images. © 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

VL - 32 SN - 0031-3203 IS - 4 N1 - UT: 000079145300005ScopusID: 0033116536doi: 10.1016/S0031-3203(98)00104-6 JO - PATTERN RECOGN ER - TY - CHAP T1 - Motion Compensated Color Video Classification Using Markov Random Fields T2 - Proceedings of Asian Conference on Computer Vision (ACCV) Y1 - 1998 JF - Proceedings of Asian Conference on Computer Vision (ACCV) PB - Springer Verlag CY - Berlin; Heidelberg N1 - doi: 10.1007/3-540-63930-6_189 ER - TY - CONF T1 - Color Image Classification and Parameter Estimation in a Markovian FrameworkProceedings of Workshop on 3D Computer Vision Y1 - 1997 UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.1560 ER - TY - ABST T1 - Image segmentation using Markov random field model in fully parallel cellular network architectures. Y1 - 1997 ER - TY - ABST T1 - Markov Random Field Image Segmentation using Cellular Neural Network Y1 - 1997 ER - TY - ABST T1 - Motion Compensated Color Image Classification and Parameter Estimation in a Markovian Framework Y1 - 1997 UR - http://biblioteca.universia.net/html_bura/ficha/params/title/motion-compensated-color-image-classification-and-parameter-estimation-in-markovian/id/5664082.html ER - TY - CONF T1 - MRF based image segmentation with fully parallel cellular nonlinear networks T2 - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 1997 Y1 - 1997 JF - A Képfeldolgozók és Alakfelismerők Társaságának konferenciája - KÉPAF 1997 PB - Pannon Agrártudományi Egyetem Georgikon Mezőgazdaságtudományi Kar CY - Keszthely ER - TY - JOUR T1 - Bayesian image classification using Markov random fields JF - IMAGE AND VISION COMPUTING Y1 - 1996 AB -

In this paper, we present three optimisation techniques, Deterministic Pseudo-Annealing (DPA), Game Strategy Approach (GSA), and Modified Metropolis Dynamics (MMD), in order to carry out image classification using a Markov random field model. For the first approach (DPA), the a posteriori probability of a tentative labelling is generalised to a continuous labelling. The merit function thus defined has the same maxima under constraints yielding probability vectors. Changing these constraints convexifies the merit function. The algorithm solves this unambiguous maximisation problem, and then tracks down the solution while the original constraints are restored yielding a good, even if suboptimal, solution to the original labelling assignment problem. In the second method (GSA), the maximisation problem of the a posteriori probability of the labelling is solved by an optimisation algorithm based on game theory. A non-cooperative n-person game with pure strategies is designed such that the set of Nash equilibrium points of the game is identical to the set of local maxima of the a posteriori probability of the labelling. The algorithm converges to a Nash equilibrium. The third method (MMD) is a modified version of the Metropolis algorithm: at each iteration the new state is chosen randomly, but the decision to accept it is purely deterministic. This is also a suboptimal technique but it is much faster than stochastic relaxation. These three methods have been implemented on a Connection Machine CM2. Experimental results are compared to those obtained by the Metropolis algorithm, the Gibbs sampler and ICM (Iterated Conditional Mode).

VL - 14 SN - 0262-8856 IS - 4 N1 - UT: A1996UT58100004ScopusID: 0030148684doi: 10.1016/0262-8856(95)01072-6 JO - IMAGE VISION COMPUT ER - TY - CHAP T1 - Cellular Neural Network in Markov Random Field Image Segmentation T2 - 1996 FOURTH IEEE INTERNATIONAL WORKSHOP ON CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS, PROCEEDINGS (CNNA-96) Y1 - 1996 JF - 1996 FOURTH IEEE INTERNATIONAL WORKSHOP ON CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS, PROCEEDINGS (CNNA-96) PB - Wiley - IEEE Press CY - New York N1 - UT: A1996BH11L00025ScopusID: 0030409916Besorolás: Konferenciaközlemény ER - TY - JOUR T1 - A Hierarchical Markov Random Field Model and Multitemperature Annealing for Parallel Image Classification JF - GRAPHICAL MODELS AND IMAGE PROCESSING Y1 - 1996 AB -

In this paper, we are interested in massively parallel multiscale relaxation algorithms applied to image classification. It is well known that multigrid methods can improve significantly the convergence rate and the quality of the final results of iterative relaxation techniques. First, we present a classical multiscale model which consists of a label pyramid and a whole observation field. The potential functions of coarser grids are derived by simple computations. The optimization problem is first solved at the higher scale by a parallel relaxation algorithm; then the next lower scale is initialized by a projection of the result. Second, we propose a hierarchical Markov random field model based on this classical model. We introduce new interactions between neighbor levels in the pyramid. It can also be seen as a way to incorporate cliques with far apart sites for a reasonable price. This model results in a relaxation algorithm with a new annealing scheme: the multitemperature annealing (MTA) scheme, which consists of associating higher temperatures to higher levels, in order to be less sensitive to local minima at coarser grids. The convergence to the global optimum is proved by a generalization of the annealing theorem of S. Geman and D. Geman (IEEE Trans. Pattern Anal. Mach. Intell. 6, 1984, 721-741). © 1996 Academic Press, Inc.

VL - 58 SN - 1077-3169 IS - 1 N1 - UT: A1996TZ03400002ScopusID: 0029732459doi: 10.1006/gmip.1996.0002 JO - GRAPH MODEL IM PROC ER - TY - JOUR T1 - DPA: a deterministic approach to the MAP problem JF - IEEE TRANSACTIONS ON IMAGE PROCESSING Y1 - 1995 AB - Deterministic pseudo-annealing (DPA) is a new deterministic optimization method for finding the maximum a posteriori (MAP) labeling in a Markov random field, in which the probability of a tentative labeling is extended to a merit function on continuous labelings. This function is made convex by changing its definition domain. This unambiguous maximization problem is solved, and the solution is followed down to the original domain, yielding a good, if suboptimal, solution to the original labeling assignment problem. The performance of DPA is analyzed on randomly weighted graphs. VL - 4 SN - 1057-7149 IS - 9 N1 - UT: A1995RT35400011ScopusID: 0029375669doi: 10.1109/83.413175 JO - IEEE T IMAGE PROCESS ER - TY - CHAP T1 - Unsupervised adaptive image segmentation T2 - ICASSP-95 Y1 - 1995 AB - This paper deals with the problem of unsupervised Bayesian segmentation of images modeled by Markov Random Fields (MRF). If the model parameters are known then we have various methods to solve the segmentation problem (Simulated Annealing, ICM, etc...). However, when they are not known, the problem becomes more difficult. One has to estimate the hidden label field parameters from the available image only. Our approach consists of a recent iterative method of estimation, called Iterative Conditional Estimation (ICE), applied to a monogrid Markovian image segmentation model. The method has been tested on synthetic and real satellite images. JF - ICASSP-95 PB - IEEE CY - Piscataway N1 - ScopusID: 0028996751doi: 10.1109/ICASSP.1995.479976 ER - TY - CHAP T1 - Unsupervised parallel image classification using a hierarchical Markovian model T2 - Proceedings of the 5th International Conference on Computer Vision Y1 - 1995 AB - This paper deals with the problem of unsupervised classification of images modeled by Markov Random Fields (MRF). If the model parameters are known then we have various methods to solve the segmentation problem (simulated annealing, ICM, etc...). However, when they are not known, the problem becomes more difficult. One has to estimate the hidden label field parameters from the only observable image. Our approach consists of extending a recent iterative method of estimation, called Iterative Conditional Estimation (ICE) to a hierarchical markovian model. The idea resembles the Estimation-Maximization (EM) algorithm as we recursively look at the Maximum a Posteriori (MAP) estimate of the label field given the estimated parameters then we look at the Maximum Likelihood (ML) estimate of the parameters given a tentative labeling obtained at the previous step. We propose unsupervised image classification algorithms using a hierarchical model. The only parameter supposed to be known is the number of regions, all the other parameters are estimated. The presented algorithms have been implemented on a Connection Machine CM200. Comparative tests have been done on noisy synthetic and real images (remote sensing). JF - Proceedings of the 5th International Conference on Computer Vision PB - IEEE CY - Piscataway N1 - ScopusID: 0029214757doi: 10.1109/ICCV.1995.466790 ER - TY - THES T1 - Multi-scale Markovian Modelisation in Computer Vision with Applications to SPOT Image Segmentation : Modélisations markoviennes multirésolutions en vision par ordinateur. Application ŕ la segmentation d'images SPOT Y1 - 1994 ER - TY - CHAP T1 - Multi-Temperature Annealing: A New Approach for the Energy-Minimization of Hierarchical Markov Random Field Models T2 - Proceedings of the 12th IAPR International Conference on Pattern Recognition Y1 - 1994 JF - Proceedings of the 12th IAPR International Conference on Pattern Recognition PB - IEEE CY - Los Alamitos N1 - doi: 10.1109/ICPR.1994.576342 ER - TY - ABST T1 - Segmentation hiérarchique d'images sur CM200 (Hierarchical Image Segmentation on the CM200) Y1 - 1994 ER - TY - ABST T1 - Segmentation multirésolution d'images sur SUN version 1 du 26.05.1994 (Multiresolution Image Segmentation on SUN version 1 of 26.05.1994) Y1 - 1994 UR - http://www.app.asso.fr/en/ ER - TY - CHAP T1 - Bayesian Image Classification Using Markov Random Fields T2 - Maximum Entropy and Bayesian Methods Y1 - 1993 JF - Maximum Entropy and Bayesian Methods PB - Kluwer Academic Publishers CY - Dordrecht; Boston; London ER - TY - ABST T1 - Extraction d'information dans les images SPOT Y1 - 1993 ER - TY - ABST T1 - A Hierarchical Markov Random Field Model and Multi-Temperature Annealing for Parallel Image Classification Y1 - 1993 UR - http://hal.inria.fr/inria-00074736/ ER - TY - CONF T1 - A Hierarchical Markov Random Field Model for Image Classification T2 - International Workshop on Image and Multidimensional Digital Signal Processing (IMDSP) Y1 - 1993 JF - International Workshop on Image and Multidimensional Digital Signal Processing (IMDSP) PB - IEEE Computer Soc. Pr. N1 - Art. No.: imdsp.ps ER - TY - CHAP T1 - Multiscale Markov random field models for parallel image classification T2 - Fourth International Conference on Computer Vision, ICCV 1993, Berlin, Germany, 11-14 May, 1993, Proceedings Y1 - 1993 AB - In this paper, we are interested in multiscale Markov Random Field (MRF) models. It is well known that multigrid methods can improve significantly the convergence rate and the quality of the final results of iterative relaxation techniques. Herein, we propose a new hierarchical model, which consists of a label pyramid and a whole observation field. The parameters of the coarse grid can be derived by simple computation from the finest grid. In the label pyramid, we have introduced a new local interaction between two neighbor grids. This model gives a relaxation algorithm which can be run in parallel on the entire pyramid. On the other hand, the new model allows to propagate local interactions more efficiently giving estimates closer to the global optimum for deterministic as well as for stochastic relaxation schemes. It can also be seen as a way to incorporate cliques with far apart sites for a reasonable price. JF - Fourth International Conference on Computer Vision, ICCV 1993, Berlin, Germany, 11-14 May, 1993, Proceedings PB - IEEE CY - Los Alamitos N1 - ScopusID: 0027224261 ER - TY - CHAP T1 - Parallel image classification using multiscale Markov random fields T2 - ICASSP-93 Y1 - 1993 AB - In this paper, we are interested in massively parallel multiscale relaxation algorithms applied to image classification. First, we present a classical multiscale model applied to supervised image classification. The model consists of a label pyramid and a whole observation field. The potential functions of the coarse grid are derived by simple computations. Then, we propose another scheme introducing a local interaction between two neighbor grids in the label pyramid. This is a way to incorporate cliques with far apart sites for a reasonable price. Finally we present the results on noisy synthetic data and on a SPOT image obtained by different relaxation methods using these models. JF - ICASSP-93 PB - IEEE CY - New York N1 - ScopusID: 0027266514doi: 10.1109/ICASSP.1993.319766 ER - TY - ABST T1 - Image Classification Using Markov Random Fields with Two New Relaxation Methods Y1 - 1992 UR - http://hal.inria.fr/docs/00/07/49/54/PDF/RR-1606.pdf ER - TY - CONF T1 - Satellite Image Classification Using a Modified Metropolis Dynamics T2 - International Conference on Acoustics, Speech and Signal Processing (ICASSP) Y1 - 1992 JF - International Conference on Acoustics, Speech and Signal Processing (ICASSP) PB - IEEE Computer Soc. Pr. N1 - doi: 10.1109/ICASSP.1992.226148 ER -