Image Segmentation through a Hierarchy of Minimum Spanning Trees

Salvatore Gaglio, Gaspare Vetrano, Ignazio Infantino, Salvatore Gaglio, Filippo Vella

Risultato della ricerca: Other

4 Citazioni (Scopus)

Abstract

Many approaches have been adopted to solve the problem of image segmentation. Among them a noticeable part is based on graph theory casting the pixels as nodes in a graph. This paper proposes an algorithm to select clusters in the images (corresponding to relevant segments in the image) corresponding to the areas induced in the images through the search of the Minimum Spanning Tree (MST). In particular it is based on a clustering algorithm that extracts clusters computing a hierarchy of Minimum Spanning Trees. The main drawback of this previous algorithm is that the dimension of the cluster is not predictable and a relevant portion of found clusters can be composed by micro-clusters that are useless in the segments computation. A new algorithm and a new metric are proposed to select the exact number of clusters and avoid unmeaningful clusters.
Lingua originaleEnglish
Pagine381-388
Numero di pagine8
Stato di pubblicazionePublished - 2012

Fingerprint

Image segmentation
Cluster computing
Graph theory
Clustering algorithms
Casting
Pixels

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Signal Processing

Cita questo

Gaglio, S., Vetrano, G., Infantino, I., Gaglio, S., & Vella, F. (2012). Image Segmentation through a Hierarchy of Minimum Spanning Trees. 381-388.

Image Segmentation through a Hierarchy of Minimum Spanning Trees. / Gaglio, Salvatore; Vetrano, Gaspare; Infantino, Ignazio; Gaglio, Salvatore; Vella, Filippo.

2012. 381-388.

Risultato della ricerca: Other

Gaglio, S, Vetrano, G, Infantino, I, Gaglio, S & Vella, F 2012, 'Image Segmentation through a Hierarchy of Minimum Spanning Trees', pagg. 381-388.
Gaglio S, Vetrano G, Infantino I, Gaglio S, Vella F. Image Segmentation through a Hierarchy of Minimum Spanning Trees. 2012.
Gaglio, Salvatore ; Vetrano, Gaspare ; Infantino, Ignazio ; Gaglio, Salvatore ; Vella, Filippo. / Image Segmentation through a Hierarchy of Minimum Spanning Trees. 8 pag.
@conference{17e4f374e5a146e7b336521fe3cc88f4,
title = "Image Segmentation through a Hierarchy of Minimum Spanning Trees",
abstract = "Many approaches have been adopted to solve the problem of image segmentation. Among them a noticeable part is based on graph theory casting the pixels as nodes in a graph. This paper proposes an algorithm to select clusters in the images (corresponding to relevant segments in the image) corresponding to the areas induced in the images through the search of the Minimum Spanning Tree (MST). In particular it is based on a clustering algorithm that extracts clusters computing a hierarchy of Minimum Spanning Trees. The main drawback of this previous algorithm is that the dimension of the cluster is not predictable and a relevant portion of found clusters can be composed by micro-clusters that are useless in the segments computation. A new algorithm and a new metric are proposed to select the exact number of clusters and avoid unmeaningful clusters.",
author = "Salvatore Gaglio and Gaspare Vetrano and Ignazio Infantino and Salvatore Gaglio and Filippo Vella",
year = "2012",
language = "English",
pages = "381--388",

}

TY - CONF

T1 - Image Segmentation through a Hierarchy of Minimum Spanning Trees

AU - Gaglio, Salvatore

AU - Vetrano, Gaspare

AU - Infantino, Ignazio

AU - Gaglio, Salvatore

AU - Vella, Filippo

PY - 2012

Y1 - 2012

N2 - Many approaches have been adopted to solve the problem of image segmentation. Among them a noticeable part is based on graph theory casting the pixels as nodes in a graph. This paper proposes an algorithm to select clusters in the images (corresponding to relevant segments in the image) corresponding to the areas induced in the images through the search of the Minimum Spanning Tree (MST). In particular it is based on a clustering algorithm that extracts clusters computing a hierarchy of Minimum Spanning Trees. The main drawback of this previous algorithm is that the dimension of the cluster is not predictable and a relevant portion of found clusters can be composed by micro-clusters that are useless in the segments computation. A new algorithm and a new metric are proposed to select the exact number of clusters and avoid unmeaningful clusters.

AB - Many approaches have been adopted to solve the problem of image segmentation. Among them a noticeable part is based on graph theory casting the pixels as nodes in a graph. This paper proposes an algorithm to select clusters in the images (corresponding to relevant segments in the image) corresponding to the areas induced in the images through the search of the Minimum Spanning Tree (MST). In particular it is based on a clustering algorithm that extracts clusters computing a hierarchy of Minimum Spanning Trees. The main drawback of this previous algorithm is that the dimension of the cluster is not predictable and a relevant portion of found clusters can be composed by micro-clusters that are useless in the segments computation. A new algorithm and a new metric are proposed to select the exact number of clusters and avoid unmeaningful clusters.

UR - http://hdl.handle.net/10447/74862

M3 - Other

SP - 381

EP - 388

ER -