Constellations and the unsupervised learning of graphs

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/23399
Información del item - Informació de l'item - Item information
Title: Constellations and the unsupervised learning of graphs
Authors: Bonev, Boyan | Escolano, Francisco | Lozano, Miguel Angel | Suau Pérez, Pablo | Cazorla, Miguel | Aguilar, Wendy
Research Group/s: Robótica y Visión Tridimensional (RoViT) | Laboratorio de Investigación en Visión Móvil (MVRLab)
Center, Department or Service: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Keywords: Unsupervised clustering of graphs | Constellation approach | Object recognition
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial
Issue Date: 2007
Publisher: Springer Berlin / Heidelberg
Citation: BONEV, Boyan, et al. "Constellations and the unsupervised learning of graphs". En: Graph-Based Representations in Pattern Recognition : 6th IAPR-TC-15 International Workshop, GbRPR 2007, Alicante, Spain, June 11-13, 2007, Proceedings / Francisco Escolano, Mario Vento (Eds.). Berlin : Springer, 2007. (Lecture Notes in Computer Science; 4538). ISBN 978-3-540-72902-0, pp. 340-350
Abstract: In this paper, we propose a novel method for the unsupervised clustering of graphs in the context of the constellation approach to object recognition. Such method is an EM central clustering algorithm which builds prototypical graphs on the basis of fast matching with graph transformations. Our experiments, both with random graphs and in realistic situations (visual localization), show that our prototypes improve the set median graphs and also the prototypes derived from our previous incremental method. We also discuss how the method scales with a growing number of images.
URI: http://hdl.handle.net/10045/23399
ISBN: 978-3-540-72902-0
ISSN: 0302-9743 (Print) | 1611-3349 (Online)
DOI: 10.1007/978-3-540-72903-7_31
Language: eng
Type: info:eu-repo/semantics/conferenceObject
Rights: The original publication is available at www.springerlink.com
Peer Review: si
Publisher version: http://dx.doi.org/10.1007/978-3-540-72903-7_31
Appears in Collections:INV - RoViT - Comunicaciones a Congresos, Conferencias, etc.

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2007_Cazorla_etal_LNCS.pdfVersión revisada (acceso abierto)2,67 MBAdobe PDFOpen Preview
Thumbnail2007_Cazorla_etal_LNCS_final.pdfVersión final (acceso restringido)4,11 MBAdobe PDFOpen    Request a copy


Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.