Publications of Zoltan Kato

Result of the query in the list of publications :

• 4 Articles
• 6 Conference articles
• 2 Technical and Research Reports
• 1 Collection article or Book chapter
• 1 Book

new search | get the bibtex

navigation : 1 - 2 display : 10 per page | 20 per page | 50 per page

4 Articles

1 - Detection of Object Motion Regions in Aerial Image Pairs with a Multi-Layer Markovian Model. C. Benedek and T. Szirányi and Z. Kato and J. Zerubia. IEEE Trans. Image Processing, 18(10): pages 2303-2315, October 2009. Keywords : Change detection, Aerial images, Camera motion, MRF. @ARTICLE{benedekTIP09, author = {Benedek, C. and Szirányi, T. and Kato, Z. and Zerubia, J.}, title = {Detection of Object Motion Regions in Aerial Image Pairs with a Multi-Layer Markovian Model}, year = {2009}, month = {October}, journal = {IEEE Trans. Image Processing}, volume = {18}, number = {10}, pages = {2303-2315}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5089480}, keyword = {Change detection, Aerial images, Camera motion, MRF} } Abstract : We propose a new Bayesian method for detecting the 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 model which integrates information from two different features, and ensures connected homogeneous regions in the segmented images. Validation is given on real aerial photos.

2 - A higher-order active contour model of a ‘gas of circles' and its application to tree crown extraction. P. Horvath and I. H. Jermyn and Z. Kato and J. Zerubia. Pattern Recognition, 42(5): pages 699-709, May 2009. Keywords : Shape, Higher-order, Active contour, Gas of circles, Tree Crown Extraction, Bayesian. @ARTICLE{Horvath09, author = {Horvath, P. and Jermyn, I. H. and Kato, Z. and Zerubia, J.}, title = {A higher-order active contour model of a ‘gas of circles' and its application to tree crown extraction}, year = {2009}, month = {May}, journal = {Pattern Recognition}, volume = {42}, number = {5}, pages = {699-709}, url = {http://dx.doi.org/10.1016/j.patcog.2008.09.008}, pdf = {http://www-sop.inria.fr/members/Ian.Jermyn/publications/Horvathetal09.pdf}, keyword = {Shape, Higher-order, Active contour, Gas of circles, Tree Crown Extraction, Bayesian} } Abstract : We present a model of a ‘gas of circles’: regions in the image domain composed of a unknown number of circles of approximately the same radius. The model has applications to medical, biological, nanotechnological, and remote sensing imaging. The model is constructed using higher-order active contours (HOACs) in order to include non-trivial prior knowledge about region shape without constraining topology. The main theoretical contribution is an analysis of the local minima of the HOAC energy that allows us to guarantee stable circles, fix one of the model parameters, and constrain the rest. We apply the model to tree crown extraction from aerial images of plantations. Numerical experiments both confirm the theoretical analysis and show the empirical importance of the prior shape information.

3 - Image segmentation using Markov random field model in fully parallel cellular network architectures. T. Szirányi and J. Zerubia and L. Czúni and D. Geldreich and Z. Kato. Real Time Imaging, 6(3): pages 195-211, June 2000. @ARTICLE{jz00y, author = {Szirányi, T. and Zerubia, J. and Czúni, L. and Geldreich, D. and Kato, Z.}, title = {Image segmentation using Markov random field model in fully parallel cellular network architectures}, year = {2000}, month = {June}, journal = {Real Time Imaging}, volume = {6}, number = {3}, pages = {195-211}, pdf = {http://dx.doi.org/10.1006/rtim.1998.0159}, keyword = {} } Abstract : Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. Herein, we show that the Markovian labeling approach can be implemented in fully parallel cellular network architectures, using simple functions and data representations. This makes possible to implement our model in parallel imaging VLSI chips. As an example, we have developed a simplified statistical image segmentation algorithm for the Cellular Neural/Nonlinear Networks Universal Machine (CNN-UM), which is a new image processing tool, containing thousands of cells with analog dynamics, local memories and processing units. The Modified Metropolis Dynamics (MMD) optimization method can be implemented into the raw analog architecture of the CNN-UM. We can introduce the whole pseudo-stochastic segmentation process in the CNN architecture using 8 memories/cell. We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw). With this architecture, the proposed VLSI CNN chip can execute a pseudo-stochastic relaxation algorithm of about 100 iterations in about 100 μs. In the suggested solution the segmentation is unsupervised, where a pixel-level statistical estimation model is used. We have tested different monogrid and multigrid architectures. In our CNN-UM model several complex preprocessing steps can be involved, such as texture-classification or anisotropic diffusion. With these preprocessing steps, our fully parallel cellular system may work as a high-level image segmentation machine, using only simple functions based on the close-neighborhood of a pixel.

4 - Unsupervised parallel image classification using Markovian models. Z. Kato and J. Zerubia and M. Berthod. Pattern Recognition, 32(4): pages 591-604, 1999. Keywords : Markov random field model, Hierarchical model, Parameter estimation, Parallel unsupervised image classification. @ARTICLE{jz99a, author = {Kato, Z. and Zerubia, J. and Berthod, M.}, title = {Unsupervised parallel image classification using Markovian models}, year = {1999}, journal = {Pattern Recognition}, volume = {32}, number = {4}, pages = {591-604}, pdf = {http://dx.doi.org/10.1016/S0031-3203(98)00104-6}, keyword = {Markov random field model, Hierarchical model, Parameter estimation, Parallel unsupervised image classification} } Abstract : 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.

top of the page

6 Conference articles

1 - A markov random field model for extracting near-circular shapes. T. Blaskovics and Z. Kato and I. H. Jermyn. In Proc. IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, November 2009. Keywords : Segmentation, Markov Random Fields, Shape prior. @INPROCEEDINGS{Blaskovics09, author = {Blaskovics, T. and Kato, Z. and Jermyn, I. H.}, title = {A markov random field model for extracting near-circular shapes}, year = {2009}, month = {November}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, address = {Cairo, Egypt}, pdf = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5413472}, keyword = {Segmentation, Markov Random Fields, Shape prior} }

2 - A Multi-Layer MRF Model for Object-Motion Detection in Unregistered Airborne Image-Pairs. C. Benedek and T. Szirányi and Z. Kato and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Vol. 6, pages 141--144, San Antonio, Texas, USA, September 2007. Keywords : Change detection, Aerial images, Camera motion, MRF. Copyright : Copyright IEEE @INPROCEEDINGS{benedek_ICIP07, author = {Benedek, C. and Szirányi, T. and Kato, Z. and Zerubia, J.}, title = {A Multi-Layer MRF Model for Object-Motion Detection in Unregistered Airborne Image-Pairs}, year = {2007}, month = {September}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, volume = {6}, pages = {141--144}, address = {San Antonio, Texas, USA}, url = {http://ieeexplore.ieee.org/search/srchabstract.jsp?arnumber=4379541&isnumber=4379494&punumber=4378863&k2dockey=4379541@ieeecnfs&query=%28benedek+%3Cin%3E+metadata%29+%3Cand%3E+%284379494+%3Cin%3E+isnumber%29&pos=0}, pdf = {http://web.eee.sztaki.hu/~bcsaba/Publications/Pdf/benedek_icip2007.pdf}, keyword = {Change detection, Aerial images, Camera motion, MRF} } Abstract : In this paper, we give a probabilistic model for automatic change detection on airborne images taken with moving cameras. To ensure robustness, we adopt an unsupervised coarse matching instead of a precise image registration. The challenge of the proposed model is to eliminate the registration errors, noise and the parallax artifacts caused by the static objects having considerable height (buildings, trees, walls etc.) from the difference image. We describe the background membership of a given image point through two different features, and introduce a novel three-layerMarkov Random Field (MRF) model to ensure connected homogenous regions in the segmented image.

3 - Circular object segmentation using higher-order active contours. P. Horvath and I. H. Jermyn and Z. Kato and J. Zerubia. In In Proc. Conference of the Hungarian Association for Image Analysis and Pattern Recognition (KEPAF'07), Debrecen, Hungary, January 2007. Note : In Hungarian Keywords : Higher-order, Tree Crown Extraction, Shape. @INPROCEEDINGS{Horvath07a, author = {Horvath, P. and Jermyn, I. H. and Kato, Z. and Zerubia, J.}, title = {Circular object segmentation using higher-order active contours}, year = {2007}, month = {January}, booktitle = {In Proc. Conference of the Hungarian Association for Image Analysis and Pattern Recognition (KEPAF'07)}, address = {Debrecen, Hungary}, note = {In Hungarian}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_Horvath07a.pdf}, keyword = {Higher-order, Tree Crown Extraction, Shape} }

4 - An improved 'gas of circles' higher-order active contour model and its application to tree crown extraction. P. Horvath and I. H. Jermyn and Z. Kato and J. Zerubia. In Proc. Indian Conference on Computer Vision, Graphics, and Image Processing (ICVGIP), Madurai, India, December 2006. Keywords : Tree Crown Extraction, Aerial images, Higher-order, Active contour, Gas of circles, Shape. @INPROCEEDINGS{Horvath06_icvgip, author = {Horvath, P. and Jermyn, I. H. and Kato, Z. and Zerubia, J.}, title = {An improved 'gas of circles' higher-order active contour model and its application to tree crown extraction}, year = {2006}, month = {December}, booktitle = {Proc. Indian Conference on Computer Vision, Graphics, and Image Processing (ICVGIP)}, address = {Madurai, India}, url = {http://dx.doi.org/10.1007/11949619_14}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_Horvath06_icvgip.pdf}, keyword = {Tree Crown Extraction, Aerial images, Higher-order, Active contour, Gas of circles, Shape} } Abstract : A central task in image processing is to find the region in the image corresponding to an entity. In a number of problems, the region takes the form of a collection of circles, eg tree crowns in remote sensing imagery; cells in biological and medical imagery. In~citeHorvath06b, a model of such regions, the `gas of circles' model, was developed based on higher-order active contours, a recently developed framework for the inclusion of prior knowledge in active contour energies. However, the model suffers from a defect. In~citeHorvath06b, the model parameters were adjusted so that the circles were local energy minima. Gradient descent can become stuck in these minima, producing phantom circles even with no supporting data. We solve this problem by calculating, via a Taylor expansion of the energy, parameter values that make circles into energy inflection points rather than minima. As a bonus, the constraint halves the number of model parameters, and severely constrains one of the two that remain, a major advantage for an energy-based model. We use the model for tree crown extraction from aerial images. Experiments show that despite the lack of parametric freedom, the new model performs better than the old, and much better than a classical active contour.

5 - A Higher-Order Active Contour Model for Tree Detection. P. Horvath and I. H. Jermyn and Z. Kato and J. Zerubia. In Proc. International Conference on Pattern Recognition (ICPR), Hong Kong, August 2006. Keywords : Active contour, Gas of circles, Higher-order, Shape, Prior, Tree Crown Extraction. @INPROCEEDINGS{horvath_icpr06, author = {Horvath, P. and Jermyn, I. H. and Kato, Z. and Zerubia, J.}, title = {A Higher-Order Active Contour Model for Tree Detection}, year = {2006}, month = {August}, booktitle = {Proc. International Conference on Pattern Recognition (ICPR)}, address = {Hong Kong}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_horvath_icpr06.pdf}, keyword = {Active contour, Gas of circles, Higher-order, Shape, Prior, Tree Crown Extraction} } Abstract : 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 re- cently 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.

6 - Shape Moments for Region-Based Active Contours. P. Horvath and A. Bhattacharya and I. H. Jermyn and J. Zerubia and Z. Kato. In Proc. Hungarian-Austrian Conference on Image Processing and Pattern Recognition, Szeged, Hungary, May 2005. @INPROCEEDINGS{horvath_hacippr05, author = {Horvath, P. and Bhattacharya, A. and Jermyn, I. H. and Zerubia, J. and Kato, Z.}, title = {Shape Moments for Region-Based Active Contours}, year = {2005}, month = {May}, booktitle = {Proc. Hungarian-Austrian Conference on Image Processing and Pattern Recognition}, address = {Szeged, Hungary}, url = {http://vision.vein.hu/HACIPPR/}, keyword = {} }

top of the page

navigation : 1 - 2 display : 10 per page | 20 per page | 50 per page

These pages were generated by