131 Hits in 2.8 sec

Multivariate statistical modeling for texture analysis using wavelet transforms

Nour-Eddine Lasmar, Yannick Berthoumieu
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
A comparative study between the proposed model and conventional models such as univariate Generalized Gaussian distribution and Multivariate Bessel K forms (MBKF) is conducted.  ...  We propose a stochastic model based on Spherically Invariant Random Vectors (SIRVs) joint density function with Weibull assumption to characterize the dependences between wavelet coefficients.  ...  Many univariate prior models such as the Generalized Gaussian distribution (GGD) [1] and the Student tdistribution model [2] have been used to successfully characterize the marginal distribution of  ... 
doi:10.1109/icassp.2010.5494963 dblp:conf/icassp/LasmarB10 fatcat:uvhvfvossrcyxlya36bkjzay4a

Wavelet-Based Texture Retrieval using Independent Component Analysis

Rui Zhang, Xiao-Ping Zhang, Ling Guan
2007 2007 IEEE International Conference on Image Processing  
generalized Gaussian density (GGD), and perform similarity measure based on the maximum likelihood criterion.  ...  accurate enough to characterize the stochastic properties of texture images.  ...  It can be observed that the parameter estimation of a multivariate distribution is required in the above problem.  ... 
doi:10.1109/icip.2007.4379591 dblp:conf/icip/ZhangZG07 fatcat:fttltkqzpvevxljfaka5pp3b2a

Generic multivariate model for color texture classification in RGB color space

Ahmed Drissi El Maliani, Mohammed El Hassouni, Yannick Berthoumieu, Driss Aboutajdine
2014 International Journal of Multimedia Information Retrieval  
7][8] is computationally expensive. 82 Based on these observations and to remedy the problem of complex nature 83 and huge variety of textures in the databases, we propose a generic multivari-84 ate model  ...  On the one hand, the generalized 15 Gamma density function offers free-shape parameters to characterize a wide 16 range of heavy-tailed densities, i.e. the genericity.  ...  Based on these conclusions, we repose on a multivariate model which 262 we call Multivariate Generalized Gamma distribution (MGΓ D) in order to 263 characterize the joint distribution of color texture  ... 
doi:10.1007/s13735-014-0071-y fatcat:jqhzlsfxqrgfrdug4irwgv2ely

Geodesics on the Manifold of Multivariate Generalized Gaussian Distributions with an Application to Multicomponent Texture Discrimination

Geert Verdoolaege, Paul Scheunders
2011 International Journal of Computer Vision  
We consider the Rao geodesic distance (GD) based on the Fisher information as a similarity measure on the manifold of zero-mean multivariate generalized Gaussian distributions (MGGD).  ...  Likewise, both uni-and multivariate generalized Gaussian models are evaluated, characterized by a fixed or a variable shape parameter.  ...  Acknowledgements This work was partially funded by the Fund for Scientific Research-Flanders (FWO-Vlaanderen).  ... 
doi:10.1007/s11263-011-0448-9 fatcat:x2ebzm2fqfhchk56z4xgovfexi

Texture feature extraction in the spatial-frequency domain for content-based image retrieval [article]

Nadia Baaziz, Omar Abahmane, Rokia Missaoui
2010 arXiv   pre-print
Image retrieval based on texture features is receiving special attention because of the omnipresence of this visual feature in most real-world images.  ...  This paper highlights the state-of-the-art and current progress relevant to texture-based image retrieval and spatial-frequency image representations.  ...  Model parameters are then reduced to the estimation of two values for each sub-band: the scale and the shape of the GGD.  ... 
arXiv:1012.5208v1 fatcat:ew5orkvrx5gvbjpym4e7d2oyne

Rotation invariant texture characterization and retrieval using steerable wavelet-domain hidden Markov models

M.N. Do, M. Vetterli
2002 IEEE transactions on multimedia  
With a small number of parameters, the new model captures both the subband marginal distributions and the dependencies across scales and orientations of the wavelet descriptors.  ...  We present a new statistical model for characterizing texture images based on wavelet-domain hidden Markov models.  ...  ACKNOWLEDGMENT The authors would like to thank A. Lozano for her help with the experiments.  ... 
doi:10.1109/tmm.2002.802019 fatcat:l6l4oon4tnd7lf4rh3z3yx3kym

A restoration framework for ultrasonic tissue characterization

M. Alessandrini, S. Maggio, J. Poree, L. De Marchi, N. Speciale, E. Franceschini, O. Bernard, O. Basset
2011 IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control  
Ultrasonic tissue characterization has become an area of intensive research. This procedure generally relies on the analysis of the unprocessed echo signal.  ...  on the choice of the prior distribution.  ...  appendix complex Generalized Gaussian pdf consider the complex random variable z = x r + jx i , where both x r and x i obey a GGd with zero mean, variance σ 2 , and shape parameter ξ. assuming mutual  ... 
doi:10.1109/tuffc.2011.2092 pmid:22083768 fatcat:ivyqbhu7pjbmrfaakv2h52kboq

Rotation-invariant texture retrieval with gaussianized steerable pyramids

G. Tzagkarakis, B. Beferull-Lozano, P. Tsakalides
2006 IEEE Transactions on Image Processing  
As a result, the feature extraction step consists of estimating the covariances between the normalized pyramid coefficients.  ...  This paper presents a novel rotation-invariant image retrieval scheme based on a transformation of the texture information via a steerable pyramid.  ...  The computational complexity increases as the neighborhood size increases, since the complexity to estimate and to calculate its inverse, , depends on its dimension ( ).  ... 
doi:10.1109/tip.2006.877356 pmid:16948315 fatcat:q23otywtnjanve2nhloxcbwmyy

Lightweight Probabilistic Texture Retrieval

R. Kwitt, A. Uhl
2010 IEEE Transactions on Image Processing  
The building blocks of our work are the Dual-Tree Complex Wavelet Transform and a number of statistical models for the coefficient magnitudes.  ...  We provide an in-depth computational analysis regarding the number of arithmetic operations required for similarity measurement and model parameter estimation.  ...  ACKNOWLEDGMENT The authors like to thank Dr. Nick Kingsbury for providing the MATLAB code to the Dual-Tree Complex Wavelet Transform (v4.3).  ... 
doi:10.1109/tip.2009.2032313 pmid:19758865 fatcat:onobouk6hnfevb5zqv57etfuz4

Joint Bayesian deconvolution and pointspread function estimation for ultrasound imaging

Ningning Zhao, Adrian Basarab, Denis Kouame, Jean-Yves Tourneret
2015 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)  
The prior of the unknown ultrasound image to be estimated is assumed to be a product of generalized Gaussian distributions.  ...  Thus, this paper proposes to build estimators of the unknown model parameters from samples generated according to the model posterior using a hybrid Gibbs sampler.  ...  Future work includes the application of our algorithm to real US data and the study of new estimation algorithms with reduced computational complexity.  ... 
doi:10.1109/isbi.2015.7163857 dblp:conf/isbi/ZhaoBKT15 fatcat:dxex7cx4yvgbxksj3wusv27fqu

Development of ICA and IVA Algorithms with Application to Medical Image Analysis [article]

Zois Boukouvalas
2018 arXiv   pre-print
We then discuss several techniques to accurately estimate the parameters of the multivariate generalized Gaussian distribution, and how to integrate them into the IVA model.  ...  on the part of the latent sources.  ...  This algorithm assumes a multivariate generalized Gaussian distribution (MGGD) for the underlying sources and through the estimation of its parameters, multivariate Gaussian and Laplacian distributions  ... 
arXiv:1801.08600v1 fatcat:nu2xlytexrcnnblws7zieo77be

Studies on Texture Segmentation Using D-Dimensional Generalized Gaussian Distribution integrated with Hierarchical Clustering

K. Naveen Kumar, K. Srinivasa Rao, Y. Srinivas, Ch. Satyanarayana
2016 International Journal of Image Graphics and Signal Processing  
This paper addresses the application of multivariate generalized Gaussian mixture probability model for segmenting the texture of an image integrating with hierarchical clustering.  ...  The initialization of model parameters is done through hierarchical clustering algorithm and moment method of estimation.  ...  INITIALIZATION OF MODEL PARAMETERS The efficiency of the EM algorithm in estimating the parameters is heavily dependent on the number of groups and the initial estimates of the model parameters j i i ij  ... 
doi:10.5815/ijigsp.2016.03.06 fatcat:rk2uk4kpn5dqjjeog32s4sskru

Complex-Valued Signal Processing: The Proper Way to Deal With Impropriety

T. Adali, P. J. Schreier, L. L. Scharf
2011 IEEE Transactions on Signal Processing  
There are two key ingredients in the statistical signal processing of complexvalued data: (1) utilizing the complete statistical characterization of complex-valued random signals; and (2) the optimization  ...  Complex-valued signals occur in many areas of science and engineering and are thus of fundamental interest.  ...  and to generate complex GGD samples can be found at  ... 
doi:10.1109/tsp.2011.2162954 fatcat:geh5hio6hvad5nzh73tz2m6am4

A Survey on Image Analysis based on Texture

Suresha M, Harisha Naik T
2017 International Journal of Advanced Research in Computer Science and Software Engineering  
This paper contains survey on numerous techniques for texture description and different types of texture images.  ...  The basic objective of this paper is to understand the research work carried out in the field of texture classification.  ...  The statistical modelling of the wavelet coefficients with the Generalized Gaussian Distribution (GGD) raises the problem of estimating its parameters.  ... 
doi:10.23956/ijarcsse/v7i6/0324 fatcat:632gxfogojejrhuhwvl27rjwc4

Parameter Estimation For Multivariate Generalized Gaussian Distributions

Frederic Pascal, Lionel Bombrun, Jean-Yves Tourneret, Yannick Berthoumieu
2013 IEEE Transactions on Signal Processing  
Due to its heavy-tailed and fully parametric form, the multivariate generalized Gaussian distribution (MGGD) has been receiving much attention for modeling extreme events in signal and image processing  ...  Various experiments conducted on synthetic and real data are presented to illustrate the theoretical derivations in terms of number of iterations and number of samples for different values of the shape  ...  Finally, it is interesting to note that complex GGDs have been recently studied in [30] , [31] and that multivariate regression models with generalized Gaussian errors have been considered in [32]  ... 
doi:10.1109/tsp.2013.2282909 fatcat:yiaioaftvbcxxkjskprsdlz6ny
« Previous Showing results 1 — 15 out of 131 results