%0 Conference Proceedings
%T Représentation par graphe de mots manuscrits dans les images pour la recherche par similarité
%A P. Wang
%A V. Eglin
%A C. Garcia
%A C. Largeron
%A Josep Llados
%A Alicia Fornes
%B Colloque International Francophone sur l'Écrit et le Document
%D 2014
%F P. Wang2014
%O DAG; 600.061; 602.006; 600.077
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2564), last updated on Thu, 10 Nov 2016 11:50:59 +0100
%X Effective information retrieval on handwritten document images has always beena challenging task. In this paper, we propose a novel handwritten word spotting approach based on graph representation. The presented model comprises both topological and morphological signatures of handwriting. Skeleton-based graphs with the Shape Context labeled vertexes are established for connected components. Each word image is represented as a sequence of graphs. In order to be robust to the handwriting variations, an exhaustive merging process based on DTW alignment results introduced in the similarity measure between word images. With respect to the computation complexity, an approximate graph edit distance approach using bipartite matching is employed for graph matching. The experiments on the George Washington dataset and the marriage records from the Barcelona Cathedral dataset demonstrate that the proposed approach outperforms the state-of-the-art structural methods.
%K word spotting
%K graph-based representation
%K shape context description
%K graph edit distance
%K DTW
%K block merging
%K query by example
%U http://refbase.cvc.uab.es/files/WEG2014c.pdf
%P 233-248