2,055 Hits in 8.3 sec

An Optimal Unsupervised Satellite Image Segmentation Approach Based On Pearson System And K-Means Clustering Algorithm Initialization

Ahmed Rekik, Mourad Zribi, Ahmed Ben Hamida, Mohamed Benjelloun
2009 Zenodo  
This paper presents an optimal and unsupervised satellite image segmentation approach based on Pearson system and k-Means Clustering Algorithm Initialization.  ...  Satellite image exploitation requires the use of different approaches, especially those founded on the unsupervised statistical segmentation principle.  ...  Unsupervised Satellite Image Segmentation Approach The approach that we are going to evoke, thereafter, is in fact an optimal unsupervised segmentation method based on the adoption of the Pearson system  ... 
doi:10.5281/zenodo.1085478 fatcat:d7fp2yxqcrd7vkfbkqvq3d622m

Mean field decomposition of a posteriori probability for MRF-based unsupervised textured image segmentation

H. Noda, M.N. Shirazi, B. Zhang, E. Kawaguchi
1999 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)  
This paper proposes a Markov random field (MRF) model-based method for unsupervised segmentation of multispectral images consisting of multiple textures.  ...  This method uses the Expectation and Maximization (EM) method for model parameter estimation, where in order to overcome the well-noticed computational problem in the expectation step, we approximate the  ...  The second approach uses the mean field approximation to calculate the Baum function [2] .  ... 
doi:10.1109/icassp.1999.757591 dblp:conf/icassp/NodaS0K99 fatcat:ififu6qmkvalnhskgphvgmbafm

Estimation of fuzzy Gaussian mixture and unsupervised statistical image segmentation

H. Caillol, W. Pieczynski, A. Hillion
1997 IEEE Transactions on Image Processing  
This paper addresses the estimation of fuzzy Gaussian distribution mixture with applications to unsupervised statistical fuzzy image segmentation.  ...  One such interpretation in image segmentation is the simultaneous appearance of several thematic classes on the same site.  ...  INTRODUCTION T HE statistical approach to the image segmentation problem requires modeling two random fields.  ... 
doi:10.1109/83.557353 pmid:18282938 fatcat:iuoqw5chebfutiupamze6h5tgm

Color image segmentation using adaptive mean shift and statistical model-based methods

Jong Hyun Park, Guee Sang Lee, Soon Young Park
2009 Computers and Mathematics with Applications  
a r t i c l e i n f o Keywords: Color image segmentation Mean-shift Mode detection Mean field annealing EM Gaussian mixture model a b s t r a c t In this paper, we propose an unsupervised segmentation  ...  The mean field annealing EM provides a global optimal solution to overcome the local maxima problem in a mixture model.  ...  The approximate cost function is defined as H 0 m (z; Θ) = − N i=1 K k=1 Z ik ε m ik , m = 1, 2, . . . . (14) To use the mean field approach as an approximation of the segmentation problem, we split the  ... 
doi:10.1016/j.camwa.2008.10.053 fatcat:ifshfnvjlzcj7lephnt4dsu5sq

Estimation of generalized mixtures and its application in image segmentation

Y. Delignon, A. Marzouki, W. Pieczynski
1997 IEEE Transactions on Image Processing  
We introduce in this work the notion of a generalized mixture and propose some methods for estimating it, along with applications to unsupervised statistical image segmentation.  ...  The different algorithms so obtained are then applied to the problem of unsupervised Bayesian image segmentation.  ...  Global Approach 1) Markovian Model and Global Segmentation: In the global approach, each is estimated from The field is a Markov random field and we will consider Ising's model, which is the simplest one  ... 
doi:10.1109/83.624951 pmid:18282892 fatcat:2xlwef6o7jhw5mcvpaexqcklrq

UNSUPERVISED TEXTURE SEGMENTATION BASED ON MULTISCALE STOCHASTIC MODELING IN WAVELET DOMAIN(Session7 Image Processing, Image Date Compression, Computer Vision, Multimedia Search, and Computer Graphics)(IWAIT2002)

Hideki Noda, Mahdad N. Shirazi, Eiji Kawaguchi
2002 ITE Technical Report  
For the sake of computatienal efi ficiency, versions of the EM algorithm and MAP estimate, which are based on the mean-field decomposition of a posteriori probability, are used for estimating model parameters  ...  on a multiscale stochastic modeling over the wavelet de-compositioR of image.  ...  We haye already proposed an unsupervised textured image segmentation method where the mean-field-based decomposition of a posteriori probability is used for parameter estimation and image segmentation  ... 
doi:10.11485/itetr.26.4.0_63 fatcat:2igus6jcdvdtnjeo63orw44e3i

Signal and Image Segmentation Using Pairwise Markov Chains

S. Derrode, W. Pieczynski
2004 IEEE Transactions on Signal Processing  
The aim of this paper is to apply the recent pairwise Markov chain model, which generalizes the hidden Markov chain one, to the unsupervised restoration of hidden data.  ...  They show the advantages of the pairwise Markov chain model with respect to the classical hidden Markov chain one for supervised and unsupervised restorations.  ...  For example, the sampling we use is the same that the sampling used in Stochastic EM [35] , which is a stochastic approximation of EM. A.  ... 
doi:10.1109/tsp.2004.832015 fatcat:hwjgvsswofb5hhyomsmcjfgyqa

A Markov random field image segmentation model for color textured images

Zoltan Kato, Ting-Chuen Pong
2006 Image and Vision Computing  
We propose a Markov random field (MRF) image segmentation model, which aims at combining color and texture features.  ...  Thus, the only hypothesis about the nature of the features is that an additive Gaussian noise model is suitable to describe the feature distribution belonging to a given class.  ...  Acknowledgements This research was partially supported by the Janos Bolyai research fellowship of the Hungarian Academy of Sciences, the Table 2 Computing times and segmentation error (misclassification  ... 
doi:10.1016/j.imavis.2006.03.005 fatcat:isoa2y74dfdwdhvmbfuz32kwqi

A K-Wishart Markov random field model for clustering of polarimetric SAR imagery

V. Akbari, G. Moser, A. P. Doulgeris, S. N. Anfinsen, T. Eltoft, S. B. Serpico
2011 2011 IEEE International Geoscience and Remote Sensing Symposium  
A new formulation of EM is developed to jointly address parameter estimation in the K-Wishart distribution and the spatial context model, and also minimization of the energy function.  ...  It is based on a Markov random field (MRF) model that integrates a K-Wishart distribution for the PolSAR data statistics conditioned to each image cluster and a Potts model for the spatial context.  ...  Unsupervised segmentation of C matrices is achieved using an expectation-maximization (EM) approach.  ... 
doi:10.1109/igarss.2011.6049317 dblp:conf/igarss/AkbariMDAES11 fatcat:dvww4lj7mzdyxp5yiinxlitfmy

Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields

R. Fjortoft, Y. Delignon, W. Pieczynski, M. Sigelle, F. Tupin
2003 IEEE Transactions on Geoscience and Remote Sensing  
This paper describes unsupervised classification of radar images in the framework of hidden Markov models and generalized mixture estimation.  ...  Hidden Markov chain models, applied to a Hilbert-Peano scan of the image, constitute a fast and robust alternative to hidden Markov random field models for spatial regularization of image analysis problems  ...  We use a coarse approximation of the stochastic gradient equation to compute .  ... 
doi:10.1109/tgrs.2003.809940 fatcat:a4bib35cvza57daq7fz2jf5ax4

SEC: Stochastic Ensemble Consensus Approach to Unsupervised SAR Sea-Ice Segmentation

Alexander Wong, David A. Clausi, Paul Fieguth
2009 2009 Canadian Conference on Computer and Robot Vision  
superior to approaches based on K-means clustering, Gamma mixture models, and Markov Random Field (MRF) models for sea-ice segmentation.  ...  Based on the probability distribution of the sub-classes, an expectation maximization (EM) approach is utilized to estimate the final class likelihoods using a Gaussian mixture model (GMM).  ...  with approaches based on K-means clustering, Gamma mixture models, and Markov Random Field (MRF) models.  ... 
doi:10.1109/crv.2009.25 dblp:conf/crv/WongCF09a fatcat:kjnoxgtanrb3bkwxrjdbbal5ri

Magnetic resonance image analysis by information theoretic criteria and stochastic site models

Yue Wang, T. Adah, Jianhua Xuan, Z. Szabo
2001 IEEE Transactions on Information Technology in Biomedicine  
To extract clinically useful information from images that might be lacking in prior knowledge, we introduce an unsupervised tissue characterization algorithm that is both statistically principled and patient  ...  We demonstrate the successful applications of the approach with synthetic data sets and then with real MR brain images.  ...  In particular, based on the statistical properties of MR pixel images, where pixel image is defined as the observed gray level associated with the pixel, use of an SFNM distribution is justified to model  ... 
doi:10.1109/4233.924805 pmid:11420993 fatcat:ozeae5ihevd7thjmlzajimfy3q

Improving 2D mesh image segmentation with Markovian Random Fields

Alex Cuadros-vargas, Leandro Gerhardinger, Mario Castro, Joao Neto, Luis Nonato
2006 Computer Graphics and Image Processing (SIBGRAPI), Proceedings of the Brazilian Symposium on  
This paper presents a novel segmentation method that combines the original Imesh image-based segmentation approach with Markovian Random Field (MRF) models.  ...  It takes an image as input, generate a mesh of triangles and, by treating the mesh as a Markovian field, produces quality unsupervised segmentation.  ...  Acknowledgements We wish to acknowledge the Brazilian financial agencies CNPq (proc. 307268/2003-9, FAPESP (proc. 04/02810-0, 03/02815-0 and 02/05243-4) and CAPES involved in financing the project that  ... 
doi:10.1109/sibgrapi.2006.26 dblp:conf/sibgrapi/Cuadros-VargasGCNN06 fatcat:sr3zic5kz5ebrdawffc54auysy

Parameter Estimation in Hidden Fuzzy Markov Random Fields and Image Segmentation

Fabien Salzenstein, Wojciech Pieczynski
1997 Graphical Models and Image Processing  
In the first case we speak of image segmentation method using a recent model using hidden fuzzy segmentation, and in the second case of hard segmenfuzzy Markov fields.  ...  The originality of this model is to use tation.  ...  We propose The unsupervised approach we present is based on a the using the iterative conditional estimation method recent models using hidden fuzzy Markov random fields.  ... 
doi:10.1006/gmip.1997.0431 fatcat:v4kspckdfzho7l25bkw55d44uq

Adaptive mouth segmentation using chromatic features

Simon Lucey, Sridha Sridharan, Vinod Chandran
2002 Pattern Recognition Letters  
In this paper a technique for adaptive segmentation is investigated using an unsupervised clustering technique incorporating the expectation maximisation (EM) algorithm across a variety of chromatic features  ...  Recently chromatic based segmentation has enjoyed some popularity for the purposes of mouth tracking due to its ability to distinguish between the two classes.  ...  Introduction Segmentation is a common approach in computer vision to track the outline or shape of an object.  ... 
doi:10.1016/s0167-8655(02)00078-8 fatcat:pgyck2fpafadbmew5p553hg3yy
« Previous Showing results 1 — 15 out of 2,055 results