English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/30156
logo share SHARE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:


Attributed graph matching for image-features association using SIFT descriptors

AuthorsSanroma, Gerard; Alquézar Mancho, Renato ; Serratosa, Francesc
KeywordsAttributed graph matching
Image registration
Discrete labeling
Pattern recognition: Image recognition
Pattern recognition
Robot vision
Pattern recognition systems
Image processing
Issue Date2010
CitationStructural, Syntactic, and Statistical Pattern Recognition: 254-263 (2010)
SeriesLecture Notes in Computer Science 6218
AbstractImage-features matching based on SIFT descriptors is subject to the misplacement of certain matches due to the local nature of the SIFT representations. Some well-known outlier rejectors aim to remove those misplaced matches by imposing geometrical consistency. We present two graph matching approaches (one continuous and one discrete) aimed at the matching of SIFT features in a geometrically consistent way. The two main novelties are that, both local and contextual coherence are imposed during the optimization process and, a model of structural consistency is presented that accounts for the quality rather than the quantity of the surrounding matches. Experimental results show that our methods achieve good results under various types of noise.
DescriptionTrabajo presentado al Joint IAPR International Workshop on Structural, Syntactic and Statistical Pattern Recognition (SSPR&SPR) celebrado en Izmir (Turquía) del 18 al 20 de agosto de 2010.
Publisher version (URL)http://dx.doi.org/10.1007/978-3-642-14980-1_24
Appears in Collections:(IRII) Libros y partes de libros
Files in This Item:
File Description SizeFormat 
Attributed graph matching.pdf146,01 kBAdobe PDFThumbnail
Show full item record
Review this work

WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.