DaLI: deformation and light invariant descriptor

Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel featu...

ver descrição completa

Detalhes bibliográficos
Autores: Simó Serra, Edgar, Torras, Carme|||0000-0002-2933-398X, Moreno-Noguer, Francesc
Tipo de documento: artigo
Data de publicação:2015
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/83179
Acesso em linha:https://hdl.handle.net/2117/83179
https://dx.doi.org/10.1007/s11263-015-0805-1
Access Level:Acceso aberto
Palavra-chave:Local image descriptors
Diffusion equation
Heat kernel descriptors
Deformation and illumination invariance
image
Recognition
Features
Segmentation
Framework
Surfaces
Classificació INSPEC::Pattern recognition::Image recognition
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
id ES_5a93a6409516ce4ffb75d85698dcf2a4
oai_identifier_str oai:upcommons.upc.edu:2117/83179
network_acronym_str ES
network_name_str España
repository_id_str
spelling DaLI: deformation and light invariant descriptorSimó Serra, EdgarTorras, Carme|||0000-0002-2933-398XMoreno-Noguer, FrancescLocal image descriptorsDiffusion equationHeat kernel descriptorsDeformation and illumination invarianceimageRecognitionFeaturesSegmentationFrameworkSurfacesClassificació INSPEC::Pattern recognition::Image recognitionÀrees temàtiques de la UPC::Informàtica::Automàtica i controlRecent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.Peer Reviewed20152015-11-0120162016-02-19journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/83179https://dx.doi.org/10.1007/s11263-015-0805-1reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengEuropean Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 269959 Intelligent observation and execution of Actions and manipulationsopen accesshttp://purl.org/coar/access_right/c_abf2http://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/831792026-05-27T15:37:01Z
dc.title.none.fl_str_mv DaLI: deformation and light invariant descriptor
title DaLI: deformation and light invariant descriptor
spellingShingle DaLI: deformation and light invariant descriptor
Simó Serra, Edgar
Local image descriptors
Diffusion equation
Heat kernel descriptors
Deformation and illumination invariance
image
Recognition
Features
Segmentation
Framework
Surfaces
Classificació INSPEC::Pattern recognition::Image recognition
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
title_short DaLI: deformation and light invariant descriptor
title_full DaLI: deformation and light invariant descriptor
title_fullStr DaLI: deformation and light invariant descriptor
title_full_unstemmed DaLI: deformation and light invariant descriptor
title_sort DaLI: deformation and light invariant descriptor
dc.creator.none.fl_str_mv Simó Serra, Edgar
Torras, Carme|||0000-0002-2933-398X
Moreno-Noguer, Francesc
author Simó Serra, Edgar
author_facet Simó Serra, Edgar
Torras, Carme|||0000-0002-2933-398X
Moreno-Noguer, Francesc
author_role author
author2 Torras, Carme|||0000-0002-2933-398X
Moreno-Noguer, Francesc
author2_role author
author
dc.subject.none.fl_str_mv Local image descriptors
Diffusion equation
Heat kernel descriptors
Deformation and illumination invariance
image
Recognition
Features
Segmentation
Framework
Surfaces
Classificació INSPEC::Pattern recognition::Image recognition
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
topic Local image descriptors
Diffusion equation
Heat kernel descriptors
Deformation and illumination invariance
image
Recognition
Features
Segmentation
Framework
Surfaces
Classificació INSPEC::Pattern recognition::Image recognition
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
description Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.
publishDate 2015
dc.date.none.fl_str_mv 2015
2015-11-01
2016
2016-02-19
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/83179
https://dx.doi.org/10.1007/s11263-015-0805-1
url https://hdl.handle.net/2117/83179
https://dx.doi.org/10.1007/s11263-015-0805-1
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 269959 Intelligent observation and execution of Actions and manipulations
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408727104225280
score 15,198674

Registros relacionados