|
|
Publications of 2000
Result of the query in the list of publications :
5 Articles |
1 - 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. |
|
2 - A variational model for image classification and restoration.
C. Samson and L. Blanc-Féraud and G. Aubert and J. Zerubia. IEEE Trans. Pattern Analysis ans Machine Intelligence, 22(5): pages 460-472, May 2000.
@ARTICLE{cs00,
|
| author |
= |
{Samson, C. and Blanc-Féraud, L. and Aubert, G. and Zerubia, J.}, |
| title |
= |
{A variational model for image classification and restoration}, |
| year |
= |
{2000}, |
| month |
= |
{May}, |
| journal |
= |
{IEEE Trans. Pattern Analysis ans Machine Intelligence}, |
| volume |
= |
{22}, |
| number |
= |
{5}, |
| pages |
= |
{460-472}, |
| keyword |
= |
{} |
| } |
|
3 - A Level Set Model for Image Classification.
C. Samson and L. Blanc-Féraud and G. Aubert and J. Zerubia. International Journal of Computer Vision, 40(3): pages 187-198, 2000.
@ARTICLE{cs00b,
|
| author |
= |
{Samson, C. and Blanc-Féraud, L. and Aubert, G. and Zerubia, J.}, |
| title |
= |
{A Level Set Model for Image Classification}, |
| year |
= |
{2000}, |
| journal |
= |
{International Journal of Computer Vision}, |
| volume |
= |
{40}, |
| number |
= |
{3}, |
| pages |
= |
{187-198}, |
| keyword |
= |
{} |
| } |
|
4 - Mise en correspondance et recalage de graphes~: application aux réseaux routiers extraits d'un couple carte/image.
C. Hivernat and X. Descombes and S. Randriamasy and J. Zerubia. Traitement du Signal, 17(1): pages 21-32, 2000.
@ARTICLE{xd00,
|
| author |
= |
{Hivernat, C. and Descombes, X. and Randriamasy, S. and Zerubia, J.}, |
| title |
= |
{Mise en correspondance et recalage de graphes~: application aux réseaux routiers extraits d'un couple carte/image}, |
| year |
= |
{2000}, |
| journal |
= |
{Traitement du Signal}, |
| volume |
= |
{17}, |
| number |
= |
{1}, |
| pages |
= |
{21-32}, |
| keyword |
= |
{} |
| } |
|
5 - Texture analysis through a Markovian modelling and fuzzy classification: Application to urban area Extraction from Satellite Images.
A. Lorette and X. Descombes and J. Zerubia. International Journal of Computer Vision, 36(3): pages 221-236, 2000.
@ARTICLE{xd00a,
|
| author |
= |
{Lorette, A. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Texture analysis through a Markovian modelling and fuzzy classification: Application to urban area Extraction from Satellite Images}, |
| year |
= |
{2000}, |
| journal |
= |
{International Journal of Computer Vision}, |
| volume |
= |
{36}, |
| number |
= |
{3}, |
| pages |
= |
{221-236}, |
| url |
= |
{http://dx.doi.org/10.1023/A:1008129103384}, |
| pdf |
= |
{http://dx.doi.org/10.1023/A:1008129103384}, |
| keyword |
= |
{} |
| } |
|
 top of the page
2 PhD Thesis and Habilitations |
1 - Contribution à la classification d'images satellitaires par approche variationnelle et équations aux dérivées partielles.
C. Samson. PhD Thesis, Universite de Nice Sophia Antipolis, September 2000.
Keywords : Classification, Restoration, Level sets, Active contour.
@PHDTHESIS{cs,
|
| author |
= |
{Samson, C.}, |
| title |
= |
{Contribution à la classification d'images satellitaires par approche variationnelle et équations aux dérivées partielles}, |
| year |
= |
{2000}, |
| month |
= |
{September}, |
| school |
= |
{Universite de Nice Sophia Antipolis}, |
| url |
= |
{http://tel.archives-ouvertes.fr/index.php?action_todo=search&view_this_doc=tel-00319709&version=1&halsid=v3rp25aeit795fqhbg1ct0dbc1}, |
| pdf |
= |
{http://tel.archives-ouvertes.fr/docs/00/31/97/09/PDF/SAMSONthesis.pdf}, |
| keyword |
= |
{Classification, Restoration, Level sets, Active contour} |
| } |
Résumé :
Ce travail est consacré au développement ainsi qu'à l'implantation de deux modèles variationnels pour la classification d'images. La classification d'images, consistant à attribuer une étiquette à chaque pixel d'une image, concerne de nombreuses applications à partir du moment où cette opération intervient très souvent à la base des chaînes de traitement et d'interprétation d'images. De nombreux modèles de classification ont déjà été développés dans un cadre stochastique ou à travers des approches structurales, mais rarement dans un contexte variationnel qui a déjà montré son efficacité dans divers domaines tels que la reconstruction ou la restauration d'images. Le premier modèle que nous proposons repose sur la minimisation d'une famille de critères dont la suite de solutions converge vers une partition des données composée de classes homogènes séparées par des contours réguliers. Cette approche entre dans le cadre des problèmes à discontinuité libre (it free discontinuity problems) et fait appel à des notions de convergence variationnelle telle que la théorie de la Gamma-convergence. La famille de fonctionnelles que nous proposons de minimiser contient un terme de régularisation, ainsi qu'un terme de classification. Lors de la convergence de cette suite de critères, le modèle change progressivement de comportement en commençant par restaurer l'image avant d'entamer le processus d'étiquetage des pixels. Parallèlement à cette approche, nous avons développé un second modèle de classification mettant en jeu un ensemble de régions et contours actifs. Nous utilisons une approche par ensembles de niveaux pour définir le critère à minimiser, cette approche ayant déjà suscité de nombreux travaux dans le cadre de la segmentation d'images. Chaque classe, et son ensemble de régions et contours associé, est défini à travers une fonction d'ensemble de niveaux. Le critère contient des termes reliés à l'information sur les régions ainsi qu'à l'information sur les contours. Nous aboutissons à la résolution d'un système d'équations aux dérivées partielles couplées et plongées dans un schéma dynamique. L'évolution de chaque région est guidée par un jeu de forces permettant d'obtenir une partition de l'image composée de classes homogènes et dont les frontières sont lisses. Nous avons mené des expériences sur de nombreuses données synthétiques ainsi que sur des images satellitaires SPOT. Nous avons également étendu ces deux modèles au cas de données multispectrales et obtenu des résultats sur des données SPOT XS que nous avons comparé à ceux obtenus par différents modèles. |
Abstract :
This work is devoted to the development and the implementation of variational models for image classification.\ Image classification, which consists in assiging a label to each pixel of a given image, concerns many applications since it is often the basic processing for many image interpretation systems. Many models have been developed within a stochastic framework or using structural approaches, but rarely within a variational framework whose efficiency has largely been proved for a wide variety of problems such as image reconstruction or restoration. The first model we propose herein is based on the minimization of a criterion family whose set of solutions in converging to a partition of the data set composed of homogeneous regions with regularized boundaries. This approach takes place within the context of free boundary problems and we use the Gamma-convergence theory for the theoretical study. The set of functionals we minimize contains a regularization term and a classification one. As the set of functionals is converging, the behavior of the model is progressively changing: the restoration process is vanishing while the labeling one is rising. The second model we propose is based on a set of active regions and contours. We use a level set formulation to define the criterion we want to minimize, this formulation allows a change of topology of the evolving sets. Each class and its associated set of regions and boundaries is defined thanks to a level set function. From the Euler equations, we solve a system of coupled partial differential equations through a dynamical scheme. The evolution of each region is governed by forces constraining the partition to be composed of homogeneous classes with smooth boundaries.\ We have conducted many experiments on both synthetic and real images. We have extended these models to the multispectral case for which the data are a set of images, and we show some results and comparisons on SPOT XS images. |
|
2 - Sur quelques Problèmes Inverses en Traitement d'Image.
L. Blanc-Féraud. Habilitation à diriger des Recherches, Universite de Nice Sophia Antipolis, July 2000.
Keywords : Partial differential equation, Restoration, Regularization, Gamma Convergence, Variational methods.
@PHDTHESIS{lbf,
|
| author |
= |
{Blanc-Féraud, L.}, |
| title |
= |
{Sur quelques Problèmes Inverses en Traitement d'Image}, |
| year |
= |
{2000}, |
| month |
= |
{July}, |
| school |
= |
{Universite de Nice Sophia Antipolis}, |
| type |
= |
{Habilitation à diriger des Recherches}, |
| url |
= |
{http://www.inria.fr/rrrt/th-020.html}, |
| ps |
= |
{ftp://ftp.inria.fr/INRIA/publication/Theses/TH-020.ps.gz}, |
| keyword |
= |
{Partial differential equation, Restoration, Regularization, Gamma Convergence, Variational methods} |
| } |
Résumé :
Après une présentation générale des problèmes inverses mal posés en imagerie, les méthodes de régularisation linéaires puis non linéaires sont présentées. La préservation des discontinuités (contours d'une image) est abordée conjointement selon 3 approches: stochastique, variationnelle et EDP. Des résultats sont montrés sur plusieurs applications dont la restauration d'image optique satellitaire, la reconstruction SPECT 2D et 3D en imagerie médicale, la diffraction inverse en imagerie microonde. Nous faisons ensuite le lien entre régularisation et segmentation dans l'approche variationnelle initialement introduite par Munford et Shah. Deux modèles ont été proposé pour approcher numériquement les discontinuités dans le cadre de la régularisation : par suite de fonctionnelles "Gamma-convergentes" et par ensemble de niveaux. Après avoir considéré l'exemple de la restauration d'image, nous avons aussi développé ces deux approches pour le problème de la classification d'image satelllitaire. Enfin, le problème de l'estimation des paramètres des fonctionnnelles est abordée et une méthode d'estimation stochastique est proposée dans le cadre de la restauration d'image floue en optique satellitaire. mots cles : methodes variationelles, diffusion (EDP), problemes inverses, regularisation, discontinuites, segmentation d'image, fonctionnelle de Mumford et Shah, Gamma-convergence, ensembles de niveaux, contours actifs, estimation de parametres, methodes MCMC, restauration d'image, classification d'image, reconstruction SPECT, diffraction inverse en imagerie micro-onde. |
Abstract :
We first describe ill-posed inverse problems in image processing, linear and nonlinear regularisation methods. Discontinuity preservation (edges of the image) is jointly presented following three approaches : stochastic, variational and by diffusion process (solving PDE's). Results are shown on several applications such as optical satellite image restoration, 2D and 3D SPECT reconstruction in medical images, inverse diffraction in microwavimages. Then we rely regularisation and segmentation problem in the variational approach as introduced by Mumford and Shah. Tow models have been proposed in order to numerically compute discontinuities in such models : by minimizing sequence of functionals which "Gamma-converge", and by using level sets models. After considering the restoration case, we have developped such methods for the problem of supervised image classification. Finally we have considered the parameter estimation problem for such fonctionnals and we describe a stochastic estimation method for the problem of satellite image restoration. Key-words : variational methods, diffusion (PDE), inverse problems, regularisation, discontinuities, image segmentation, Mumford and Shah functional, Gamma-convergence, level set methods, active contours, parameter estimation, MCMC methods, image restoration, supervised image classification, SPECT reconstruction, inverse diffraction in microwave images. |
|
top of the page
10 Conference articles |
1 - Regularisation by convolution in probability density estimation is equivalent to jittering.
C. Molina and J. Zerubia. In Proc. IEEE International Workshop on Neural Networks for Signal Processing (NNSP), Sydney, Australie, December 2000.
@INPROCEEDINGS{jz,
|
| author |
= |
{Molina, C. and Zerubia, J.}, |
| title |
= |
{Regularisation by convolution in probability density estimation is equivalent to jittering}, |
| year |
= |
{2000}, |
| month |
= |
{December}, |
| booktitle |
= |
{Proc. IEEE International Workshop on Neural Networks for Signal Processing (NNSP)}, |
| address |
= |
{Sydney, Australie}, |
| keyword |
= |
{} |
| } |
|
2 - Modelling SAR images with a generalisation of the Raylegh distribution.
E.E. Kuruoglu and J. Zerubia. In Asilomar Conference, Pacific Grove, USA, October 2000.
@INPROCEEDINGS{jz00w,
|
| author |
= |
{Kuruoglu, E.E. and Zerubia, J.}, |
| title |
= |
{Modelling SAR images with a generalisation of the Raylegh distribution}, |
| year |
= |
{2000}, |
| month |
= |
{October}, |
| booktitle |
= |
{Asilomar Conference}, |
| address |
= |
{Pacific Grove, USA}, |
| keyword |
= |
{} |
| } |
|
3 - Satellite image deconvolution using complex wavelet packets.
A. Jalobeanu and L. Blanc-Féraud and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Vancouver, Canada, September 2000.
@INPROCEEDINGS{jalo00c,
|
| author |
= |
{Jalobeanu, A. and Blanc-Féraud, L. and Zerubia, J.}, |
| title |
= |
{Satellite image deconvolution using complex wavelet packets}, |
| year |
= |
{2000}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Vancouver, Canada}, |
| keyword |
= |
{} |
| } |
|
top of the page
These pages were generated by 
|
get the bibtex
