Results 1 
3 of
3
Unsupervised image segmentation using triplet Markov fields
 Computer Vision and Image Understanding
, 2005
"... www.elsevier.com/locate/cviu Hidden Markov fields (HMF) models are widely applied to various problems arising in image processing. In these models, the hidden process of interest X is a Markov field and must be estimated from its observable noisy version Y. The success of HMF is mainly due to the fa ..."
Abstract

Cited by 14 (5 self)
 Add to MetaCart
www.elsevier.com/locate/cviu Hidden Markov fields (HMF) models are widely applied to various problems arising in image processing. In these models, the hidden process of interest X is a Markov field and must be estimated from its observable noisy version Y. The success of HMF is mainly due to the fact that the conditional probability distribution of the hidden process with respect to the observed one remains Markovian, which facilitates different processing strategies such as Bayesian restoration. HMF have been recently generalized to ‘‘pairwise’ ’ Markov fields (PMF), which offer similar processing advantages and superior modeling capabilities. In PMF one directly assumes the Markovianity of the pair (X,Y). Afterwards, ‘‘triplet’ ’ Markov fields (TMF), in which the distribution of the pair (X,Y) is the marginal distribution of a Markov field (X,U,Y), where U is an auxiliary process, have been proposed and still allow restoration processing. The aim of this paper is to propose a new parameter estimation method adapted to TMF, and to study the corresponding unsupervised image segmentation methods. The latter are validated via experiments and real image processing.
Text Augmentation: Inserting XML tags into natural language text with PPM Models and Viterbilike search
, 2003
"... This thesis develops work on using Hidden Markov Models to insert tags natural language text. A taxonomy of tags is developed unifying the fields of text segmentation tagging, partofspeech tagging, proper noun extraction and hierarchical entity extraction. The search spaces for inserting tags are ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
This thesis develops work on using Hidden Markov Models to insert tags natural language text. A taxonomy of tags is developed unifying the fields of text segmentation tagging, partofspeech tagging, proper noun extraction and hierarchical entity extraction. The search spaces for inserting tags are examined from both a theoretical and experimental point of view across the taxonomy and on four corpora. A analysis of different correctness measures for different types of tag insertion problem is undertaken and a technique to determine whether taginsertion errors are the result of a modelling failure or a searching failure is discovered.
Parallel Restricted Maximum Likelihood Estimation for Models with a Dense Exogenous Matrix
, 2000
"... Maximum likelihood estimates of covariance matrices for linear models occur in many statistical and stochastic applications such as estimating the genetic potential of cattle, financial time series analysis, the characterization of chemical mixtures and in general in the estimation of the parameters ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Maximum likelihood estimates of covariance matrices for linear models occur in many statistical and stochastic applications such as estimating the genetic potential of cattle, financial time series analysis, the characterization of chemical mixtures and in general in the estimation of the parameters for stochastic differential equations. Restricted Maximum Likelihood (REML) is widely used in application areas where sampling bias is an important concern, but REML estimates are expensive to compute. Parallel implementations solely based on parallel dense matrix kernels need not scale well. This paper demonstrates that it is possible to compute estimates of covariance matrix for linear models based on restricted maximum likelihood (REML) efficiently on parallel computers. Two approaches to computing in parallel the gradient of the REML objective function are presented and compared. The covariance matrix is not assumed block diagonal. The implementations presented are based on PETSc and can run on any parallel computer supporting MPI.