Skeletonization of sparse shapes using dynamic competitive neural networks

Mostrar todas las versiones(2)

The detection of regions and objects in digital images is a topic of utmost importance for solving several problems related to the area of pattern recognition. In this direction, skeletonization algorithms are a widely used tool since they allow us to reduce the quantity of available data, easing th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hasperué, Waldo, Corbalán, Leonardo César, Lanzarini, Laura Cristina, Bria, Oscar N.
Formato:	Articulo
Lenguaje:	Inglés
Publicado:	2007
Materias:	Ciencias Informáticas Skeletonization Dynamic self-organizing maps Neural networks Digital image processing
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/127869 http://journal.iberamia.org/public/ia-old/articles/540/article%20%281%29.pdf
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-127869
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Skeletonization Dynamic self-organizing maps Neural networks Digital image processing
spellingShingle	Ciencias Informáticas Skeletonization Dynamic self-organizing maps Neural networks Digital image processing Hasperué, Waldo Corbalán, Leonardo César Lanzarini, Laura Cristina Bria, Oscar N. Skeletonization of sparse shapes using dynamic competitive neural networks
topic_facet	Ciencias Informáticas Skeletonization Dynamic self-organizing maps Neural networks Digital image processing
description	The detection of regions and objects in digital images is a topic of utmost importance for solving several problems related to the area of pattern recognition. In this direction, skeletonization algorithms are a widely used tool since they allow us to reduce the quantity of available data, easing the detection of characteristics for their recognition and classification. In addition, this transformation of the original data in its essential characteristics eases the elimination of local noise which is present in the data input. This paper proposes a new skeletonization strategy applicable to sparse images from a competitive, dynamic neural network trained with the AVGSOM method. The strategy developed in this paper determines the arc making up the skeleton combining AVGSOM non-supervised learning with a minimum spanning tree. The proposed method has been applied in images with different spanning shape and degree. In particular, the results obtained have been compared to existing solutions, showing successful results. Finally, some conclusions, together with some future lines of work, are presented.
format	Articulo Articulo
author	Hasperué, Waldo Corbalán, Leonardo César Lanzarini, Laura Cristina Bria, Oscar N.
author_facet	Hasperué, Waldo Corbalán, Leonardo César Lanzarini, Laura Cristina Bria, Oscar N.
author_sort	Hasperué, Waldo
title	Skeletonization of sparse shapes using dynamic competitive neural networks
title_short	Skeletonization of sparse shapes using dynamic competitive neural networks
title_full	Skeletonization of sparse shapes using dynamic competitive neural networks
title_fullStr	Skeletonization of sparse shapes using dynamic competitive neural networks
title_full_unstemmed	Skeletonization of sparse shapes using dynamic competitive neural networks
title_sort	skeletonization of sparse shapes using dynamic competitive neural networks
publishDate	2007
url	http://sedici.unlp.edu.ar/handle/10915/127869 http://journal.iberamia.org/public/ia-old/articles/540/article%20%281%29.pdf
work_keys_str_mv	AT hasperuewaldo skeletonizationofsparseshapesusingdynamiccompetitiveneuralnetworks AT corbalanleonardocesar skeletonizationofsparseshapesusingdynamiccompetitiveneuralnetworks AT lanzarinilauracristina skeletonizationofsparseshapesusingdynamiccompetitiveneuralnetworks AT briaoscarn skeletonizationofsparseshapesusingdynamiccompetitiveneuralnetworks
bdutipo_str	Repositorios
_version_	1764820451423420416

Skeletonization of sparse shapes using dynamic competitive neural networks

Ejemplares similares