Using physical principles in the segmentation of objects represented in images

Detalhes bibliográficos
Autor(a) principal: Patrícia C. T. Gonçalves
Data de Publicação: 2008
Outros Autores: João Manuel R. S. Tavares, R. M. Natal Jorge
Tipo de documento: Livro
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://hdl.handle.net/10216/6632
Resumo: Usually, image segmentation is the first high-level task to extract information from an image, which can constitute one of the first steps to build a solid model of an organ and other structures of the human body, for example. Region segmentation distinguishes different areas of an image, and contour segmentation delimits the different regions by their frontiers. The main goal of this work is to extract the contour of an object represented in an image after the definition of an initial contour for it. This contour, roughly defined by the user, will evolve along an iterative process until it reaches the border of the desired object. For that purpose, deformable models are used, whose behaviour is guide by physical principles. To determine that behaviour, the dynamic equilibrium equation, also known as equation of motion, is applied to an elastic physical model of the contour used in the segmentation process. The first step of the methodology used in this work consists in drawing on the input image a contour shape suitable for the object to segment, which is considered as the initial segmentation contour for that object. Next, this contour is modelled according to physical principles using the Finite Elements Method. To move the physical model step forward to the border of the object to segment, the dynamic equilibrium equation is resolved having as stop criterion the equilibrium between the internal and external forces involved. The internal forces applied on the finite element model are defined based on the physical characteristics of the virtual material adopted for the model and the choose level of interaction between its nodes; and the external forces are defined in terms of the image features that best describe the object to segment, like edges for instance. The desired contour segmentation is achieved when all forces applied on the physical model are in equilibrium.
id RCAP_ba5f173b4a11969ec1e8c4c467bbf7f2
oai_identifier_str oai:repositorio-aberto.up.pt:10216/6632
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Using physical principles in the segmentation of objects represented in imagesEngenhariaEngineeringUsually, image segmentation is the first high-level task to extract information from an image, which can constitute one of the first steps to build a solid model of an organ and other structures of the human body, for example. Region segmentation distinguishes different areas of an image, and contour segmentation delimits the different regions by their frontiers. The main goal of this work is to extract the contour of an object represented in an image after the definition of an initial contour for it. This contour, roughly defined by the user, will evolve along an iterative process until it reaches the border of the desired object. For that purpose, deformable models are used, whose behaviour is guide by physical principles. To determine that behaviour, the dynamic equilibrium equation, also known as equation of motion, is applied to an elastic physical model of the contour used in the segmentation process. The first step of the methodology used in this work consists in drawing on the input image a contour shape suitable for the object to segment, which is considered as the initial segmentation contour for that object. Next, this contour is modelled according to physical principles using the Finite Elements Method. To move the physical model step forward to the border of the object to segment, the dynamic equilibrium equation is resolved having as stop criterion the equilibrium between the internal and external forces involved. The internal forces applied on the finite element model are defined based on the physical characteristics of the virtual material adopted for the model and the choose level of interaction between its nodes; and the external forces are defined in terms of the image features that best describe the object to segment, like edges for instance. The desired contour segmentation is achieved when all forces applied on the physical model are in equilibrium.20082008-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bookapplication/pdfhttps://hdl.handle.net/10216/6632engPatrícia C. T. GonçalvesJoão Manuel R. S. TavaresR. M. Natal Jorgeinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-29T12:26:19Zoai:repositorio-aberto.up.pt:10216/6632Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T23:20:20.494133Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Using physical principles in the segmentation of objects represented in images
title Using physical principles in the segmentation of objects represented in images
spellingShingle Using physical principles in the segmentation of objects represented in images
Patrícia C. T. Gonçalves
Engenharia
Engineering
title_short Using physical principles in the segmentation of objects represented in images
title_full Using physical principles in the segmentation of objects represented in images
title_fullStr Using physical principles in the segmentation of objects represented in images
title_full_unstemmed Using physical principles in the segmentation of objects represented in images
title_sort Using physical principles in the segmentation of objects represented in images
author Patrícia C. T. Gonçalves
author_facet Patrícia C. T. Gonçalves
João Manuel R. S. Tavares
R. M. Natal Jorge
author_role author
author2 João Manuel R. S. Tavares
R. M. Natal Jorge
author2_role author
author
dc.contributor.author.fl_str_mv Patrícia C. T. Gonçalves
João Manuel R. S. Tavares
R. M. Natal Jorge
dc.subject.por.fl_str_mv Engenharia
Engineering
topic Engenharia
Engineering
description Usually, image segmentation is the first high-level task to extract information from an image, which can constitute one of the first steps to build a solid model of an organ and other structures of the human body, for example. Region segmentation distinguishes different areas of an image, and contour segmentation delimits the different regions by their frontiers. The main goal of this work is to extract the contour of an object represented in an image after the definition of an initial contour for it. This contour, roughly defined by the user, will evolve along an iterative process until it reaches the border of the desired object. For that purpose, deformable models are used, whose behaviour is guide by physical principles. To determine that behaviour, the dynamic equilibrium equation, also known as equation of motion, is applied to an elastic physical model of the contour used in the segmentation process. The first step of the methodology used in this work consists in drawing on the input image a contour shape suitable for the object to segment, which is considered as the initial segmentation contour for that object. Next, this contour is modelled according to physical principles using the Finite Elements Method. To move the physical model step forward to the border of the object to segment, the dynamic equilibrium equation is resolved having as stop criterion the equilibrium between the internal and external forces involved. The internal forces applied on the finite element model are defined based on the physical characteristics of the virtual material adopted for the model and the choose level of interaction between its nodes; and the external forces are defined in terms of the image features that best describe the object to segment, like edges for instance. The desired contour segmentation is achieved when all forces applied on the physical model are in equilibrium.
publishDate 2008
dc.date.none.fl_str_mv 2008
2008-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/book
format book
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10216/6632
url https://hdl.handle.net/10216/6632
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799135502543093761