On the role of contrast and regularity in perceptual boundary saliency

Mostrar todas las versiones(2)

Mathematical Morphology proposes to extract shapes from images as connected components of level sets. These methods prove very suitable for shape recognition and analysis. We present a method to select the perceptually significant (i.e., contrasted) level lines (boundaries of level sets), using the...

Descripción completa

Detalles Bibliográficos
Autor principal:	Tepper, Mariano Hernán
Publicado:	2014
Materias:	Edge detection Helmholtz principle Level lines Topographic maps Maps Mathematical morphology Connected component Level Set Natural images Shape recognition Topographic map Numerical methods
Acceso en línea:	https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_09249907_v48_n3_p396_Tepper http://hdl.handle.net/20.500.12110/paper_09249907_v48_n3_p396_Tepper
Aporte de:	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

id	paper:paper_09249907_v48_n3_p396_Tepper
record_format	dspace
spelling	paper:paper_09249907_v48_n3_p396_Tepper2023-06-08T15:51:12Z On the role of contrast and regularity in perceptual boundary saliency Tepper, Mariano Hernán Edge detection Helmholtz principle Level lines Topographic maps Edge detection Maps Mathematical morphology Connected component Helmholtz principle Level lines Level Set Natural images Shape recognition Topographic map Numerical methods Mathematical Morphology proposes to extract shapes from images as connected components of level sets. These methods prove very suitable for shape recognition and analysis. We present a method to select the perceptually significant (i.e., contrasted) level lines (boundaries of level sets), using the Helmholtz principle as first proposed by Desolneux et al. Contrarily to the classical formulation by Desolneux et al. where level lines must be entirely salient, the proposed method allows to detect partially salient level lines, thus resulting in more robust and more stable detections. We then tackle the problem of combining two gestalts as a measure of saliency and propose a method that reinforces detections. Results in natural images show the good performance of the proposed methods. © 2013 Springer Science+Business Media New York. Fil:Tepper, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2014 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_09249907_v48_n3_p396_Tepper http://hdl.handle.net/20.500.12110/paper_09249907_v48_n3_p396_Tepper
institution	Universidad de Buenos Aires
institution_str	I-28
repository_str	R-134
collection	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic	Edge detection Helmholtz principle Level lines Topographic maps Edge detection Maps Mathematical morphology Connected component Helmholtz principle Level lines Level Set Natural images Shape recognition Topographic map Numerical methods
spellingShingle	Edge detection Helmholtz principle Level lines Topographic maps Edge detection Maps Mathematical morphology Connected component Helmholtz principle Level lines Level Set Natural images Shape recognition Topographic map Numerical methods Tepper, Mariano Hernán On the role of contrast and regularity in perceptual boundary saliency
topic_facet	Edge detection Helmholtz principle Level lines Topographic maps Edge detection Maps Mathematical morphology Connected component Helmholtz principle Level lines Level Set Natural images Shape recognition Topographic map Numerical methods
description	Mathematical Morphology proposes to extract shapes from images as connected components of level sets. These methods prove very suitable for shape recognition and analysis. We present a method to select the perceptually significant (i.e., contrasted) level lines (boundaries of level sets), using the Helmholtz principle as first proposed by Desolneux et al. Contrarily to the classical formulation by Desolneux et al. where level lines must be entirely salient, the proposed method allows to detect partially salient level lines, thus resulting in more robust and more stable detections. We then tackle the problem of combining two gestalts as a measure of saliency and propose a method that reinforces detections. Results in natural images show the good performance of the proposed methods. © 2013 Springer Science+Business Media New York.
author	Tepper, Mariano Hernán
author_facet	Tepper, Mariano Hernán
author_sort	Tepper, Mariano Hernán
title	On the role of contrast and regularity in perceptual boundary saliency
title_short	On the role of contrast and regularity in perceptual boundary saliency
title_full	On the role of contrast and regularity in perceptual boundary saliency
title_fullStr	On the role of contrast and regularity in perceptual boundary saliency
title_full_unstemmed	On the role of contrast and regularity in perceptual boundary saliency
title_sort	on the role of contrast and regularity in perceptual boundary saliency
publishDate	2014
url	https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_09249907_v48_n3_p396_Tepper http://hdl.handle.net/20.500.12110/paper_09249907_v48_n3_p396_Tepper
work_keys_str_mv	AT teppermarianohernan ontheroleofcontrastandregularityinperceptualboundarysaliency
_version_	1768543617203306496

On the role of contrast and regularity in perceptual boundary saliency

Ejemplares similares