About: Thin Structures Segmentation Using Anisotropic Neighborhoods

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Thin Structures Segmentation Using Anisotropic Neighborhoods Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Thin Structures Segmentation Using Anisotropic Neighborhoods
Creator	Le Hégarat-Mascle, Sylvie Lermé, Nicolas Ribal, Christophe
topic	covid:f187df682b7f8a87a4b76d6896833b22017d585f#this
Source	PMC
abstract	Bayesian and probabilistic models are widely used in image processing to handle noise due to various alteration phenomena. To benefit from the spatial information in a tractable way, Markov Random Fields (MRF) are often assumed with isotropic neighborhoods, that is however at the detriment of the preservation of thin structures. In this study, we aim at relaxing this assumption on stationarity and isotropy of the neighborhood shape in order to get a prior probability term that is relevant not only within the homogeneous areas but also close to object borders and within thin structures. To tackle the issue of neighborhood shape estimation, we propose to use tensor voting, that allows for the estimation of structure direction and saliency at various scales. We propose three main ways to derive anisotropic neighborhoods, namely shape-based, target-based and cardinal-based neighborhood. Then, having defined the neighborhood field, we introduce an energy that will be minimized using graph cuts, and illustrate the benefits of our approach against the use of isotropic neighborhoods in the applicative context of crack detection. First results on such a challenging problem are very encouraging.
has issue date	2020-05-18(xsd:dateTime)
bibo:doi	10.1007/978-3-030-50146-4_44
has license	no-cc
sha1sum (hex)	f187df682b7f8a87a4b76d6896833b22017d585f
schema:url	https://doi.org/10.1007/978-3-030-50146-4_44
resource representing a document's title	Thin Structures Segmentation Using Anisotropic Neighborhoods
has PubMed Central identifier	PMC7274353
schema:publication	Information Processing and Management of Uncertainty in Knowledge-Based Systems
resource representing a document's body	covid:f187df682b7f8a87a4b76d6896833b22017d585f#body_text
is http://vocab.deri.ie/void#inDataset of	proxy:http/ns.inria.fr/covid19/f187df682b7f8a87a4b76d6896833b22017d585f
is schema:about of	named entity 'problem' named entity 'detection' named entity 'BORDERS' named entity 'USED' named entity 'OUR APPROACH' named entity 'NOISE' named entity 'INFORMATION' named entity 'USE OF' named entity 'ORDER' named entity 'SPATIAL' named entity 'CARDINAL' named entity 'ALLOWS' named entity 'STRUCTURES' named entity 'VARIOUS' named entity 'NEIGHBORHOOD' named entity 'CONTEXT' named entity 'AREAS' named entity 'DUE TO' named entity 'NEIGHBORHOODS' named entity 'TO OBJECT' named entity 'study' named entity 'saliency' named entity 'minimized' named entity 'graph' named entity 'homogeneous' named entity 'illustrate' named entity 'prior probability' named entity 'regularization' named entity 'direction' named entity 'stationarity' named entity 'structure' named entity 'isotropic' named entity 'thin' named entity 'field' named entity 'Anisotropic' named entity 'graph cuts' named entity 'Segmentation' named entity 'regularization' named entity 'graph cuts' named entity 'finite set' named entity 'pixel' named entity 'isotropic' named entity 'isotropic' named entity 'regularization parameter' named entity 'pixel' named entity 'Eigenvectors' named entity 'vectors' named entity 'ground truth' named entity 'pixel' named entity 'affine function' named entity 'feature vector' named entity 'tensor' named entity 'conditional independence' named entity 'square window' named entity 'Tensor' named entity 'centroid' named entity 'Potts model' named entity 'isotropic' named entity 'scalar product' named entity 'anisotropic' named entity 'regularization' named entity 'pixel' named entity 'false negatives' named entity 'regularization' named entity 'eigenvectors' named entity 'anisotropic' named entity 'F-measure' named entity 'image segmentation' named entity 'isotropic' named entity 'regularization' named entity 'cardinality' named entity 'isotropic' named entity 'image data' named entity 'cardinality' named entity 'discretize' named entity 'ellipse' named entity 'n-dimensional space' named entity 'graph cuts' named entity 'image smoothing'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software