A new approach to image segmentation with two-dimensional hidden Markov models

Image segmentation is one of the fundamental problems in computer vision. In this work, we present a new segmentation algorithm that is based on the theory of twodimensional hidden Markov models (2D-HMM). Unlike most 2DHMM approaches we do not apply the Viterbi Algorithm, instead we present a com...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Baumgartner, Josef, Flesia, Ana Georgina, Gimenez, Javier, Pucheta, Julian
Formato: conferenceObject
Lenguaje:Inglés
Publicado: 2021
Materias:
Classification
Agriculture
Markov Models
Hidden Markov chains
Acceso en línea:http://hdl.handle.net/11086/21146
Aporte de:
Repositorio Digital Universitario (UNC) de Universidad Nacional de Córdoba
id I10-R14111086-21146
record_format dspace
institution Universidad Nacional de Córdoba
institution_str I-10
repository_str R-141
collection Repositorio Digital Universitario (UNC)
language Inglés
topic Classification
Agriculture
Markov Models
Hidden Markov chains
spellingShingle Classification
Agriculture
Markov Models
Hidden Markov chains
Baumgartner, Josef
Flesia, Ana Georgina
Gimenez, Javier
Pucheta, Julian
A new approach to image segmentation with two-dimensional hidden Markov models
topic_facet Classification
Agriculture
Markov Models
Hidden Markov chains
description Image segmentation is one of the fundamental problems in computer vision. In this work, we present a new segmentation algorithm that is based on the theory of twodimensional hidden Markov models (2D-HMM). Unlike most 2DHMM approaches we do not apply the Viterbi Algorithm, instead we present a computationally efficient algorithm that propagates the state probabilities through the image. This approach can easily be extended to higher dimensions. We compare the proposed method with a 2D-HMM standard algorithm and Iterated Conditional Modes using real world images like a radiography or a satellite image as well as synthetic images. The experimental results show that our approach is highly capable of condensing image segments. This gives our algorithm a significant advantage over the standard algorithm when dealing with noisy images with few classes.
format conferenceObject
author Baumgartner, Josef
Flesia, Ana Georgina
Gimenez, Javier
Pucheta, Julian
author_facet Baumgartner, Josef
Flesia, Ana Georgina
Gimenez, Javier
Pucheta, Julian
author_sort Baumgartner, Josef
title A new approach to image segmentation with two-dimensional hidden Markov models
title_short A new approach to image segmentation with two-dimensional hidden Markov models
title_full A new approach to image segmentation with two-dimensional hidden Markov models
title_fullStr A new approach to image segmentation with two-dimensional hidden Markov models
title_full_unstemmed A new approach to image segmentation with two-dimensional hidden Markov models
title_sort new approach to image segmentation with two-dimensional hidden markov models
publishDate 2021
url http://hdl.handle.net/11086/21146
work_keys_str_mv AT baumgartnerjosef anewapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT flesiaanageorgina anewapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT gimenezjavier anewapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT puchetajulian anewapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT baumgartnerjosef newapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT flesiaanageorgina newapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT gimenezjavier newapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
AT puchetajulian newapproachtoimagesegmentationwithtwodimensionalhiddenmarkovmodels
bdutipo_str Repositorios
_version_ 1764820395035197442

Ejemplares similares