@InProceedings{PauRiba2017,
author="Pau Riba
and Josep Llados
and Alicia Fornes",
editor="Pasquale Foggia
and Cheng-Lin Liu
and Mario Vento",
title="Error-tolerant coarse-to-fine matching model for hierarchical graphs",
booktitle="11th IAPR-TC-15 International Workshop on Graph-Based Representations in Pattern Recognition",
year="2017",
publisher="Springer International Publishing",
volume="10310",
pages="107--117",
optkeywords="Graph  matching",
optkeywords="Hierarchical  graph",
optkeywords="Graph-based  representation",
optkeywords="Coarse-to-fine matching",
abstract="Graph-based  representations  are  effective  tools  to  capture structural information from visual elements. However, retrieving a query graph  from  a  large  database  of  graphs  implies  a  high  computational complexity. Moreover, these representations are very sensitive to noise or small changes. In this work, a novel hierarchical graph representation is designed. Using graph clustering techniques adapted from graph-based social  media  analysis,  we propose  to  generate a  hierarchy  able  to  deal with different levels of abstraction while keeping information about the topology.  For  the  proposed  representations,  a  coarse-to-fine  matching method is defined. These approaches are validated using real scenarios such as classification of colour images and handwritten word spotting.",
optnote="DAG; 600.097; 601.302; 600.121",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=2951), last updated on Mon, 07 Dec 2020 14:29:44 +0100",
doi="10.1007/978-3-319-58961-9",
file=":http://refbase.cvc.uab.es/files/RLF2017.pdf:PDF"
}