On segmentation with Markovian models

This paper addresses the image modeling problem under the assumption that images can be represented by 2d order, hidden Markov random fields models. The modeling applications we have in mind com- prise pixelwise segmentation of gray-level images coming from the field of Oral Radiographic Differentia...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Flesia, Ana Georgina, Giménez, Javier, Baumgartner, Josef
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2013
Materias:
Ciencias Informáticas
comprise pixelwise segmentation
Modeling
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/76153
http://42jaiio.sadio.org.ar/proceedings/simposios/Trabajos/ASAI/06.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-76153
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
comprise pixelwise segmentation
Modeling
spellingShingle Ciencias Informáticas
comprise pixelwise segmentation
Modeling
Flesia, Ana Georgina
Giménez, Javier
Baumgartner, Josef
On segmentation with Markovian models
topic_facet Ciencias Informáticas
comprise pixelwise segmentation
Modeling
description This paper addresses the image modeling problem under the assumption that images can be represented by 2d order, hidden Markov random fields models. The modeling applications we have in mind com- prise pixelwise segmentation of gray-level images coming from the field of Oral Radiographic Differential Diagnosis. Segmentation is achieved by approximations to the solution of the maximum a posteriori equation (MAP) when the emission distribution is assumed the same in all models and the difference lays in the Neighborhood Markovian hypothesis made over the labeling random field. For two algorithms, 2d path-constrained Viterbi training and Potts-ICM we investigate goodness of fit by study- ing statistical complexity, computational gain, extent of automation, and rate of classification measured with kappa statistic. All code written is provided in a Matlab toolbox available for download from our website, following the Reproducible Research Paradigm.
format Objeto de conferencia
Objeto de conferencia
author Flesia, Ana Georgina
Giménez, Javier
Baumgartner, Josef
author_facet Flesia, Ana Georgina
Giménez, Javier
Baumgartner, Josef
author_sort Flesia, Ana Georgina
title On segmentation with Markovian models
title_short On segmentation with Markovian models
title_full On segmentation with Markovian models
title_fullStr On segmentation with Markovian models
title_full_unstemmed On segmentation with Markovian models
title_sort on segmentation with markovian models
publishDate 2013
url http://sedici.unlp.edu.ar/handle/10915/76153
http://42jaiio.sadio.org.ar/proceedings/simposios/Trabajos/ASAI/06.pdf
work_keys_str_mv AT flesiaanageorgina onsegmentationwithmarkovianmodels
AT gimenezjavier onsegmentationwithmarkovianmodels
AT baumgartnerjosef onsegmentationwithmarkovianmodels
bdutipo_str Repositorios
_version_ 1764820487826833411

Ejemplares similares