%0 Journal Article
%T Relational Indexing of Vectorial Primitives for Symbol Spotting in Line-Drawing Images
%A Marçal Rusiñol
%A Agnes Borras
%A Josep Llados
%J Pattern Recognition Letters
%D 2010
%V 31
%N 3
%I Elsevier
%F Marçal Rusiñol2010
%O DAG
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1177), last updated on Thu, 21 Jun 2012 12:32:05 +0200
%X This paper presents a symbol spotting approach for indexing by content a database of line-drawing images. As line-drawings are digital-born documents designed by vectorial softwares, instead of using a pixel-based approach, we present a spotting method based on vector primitives. Graphical symbols are represented by a set of vectorial primitives which are described by an off-the-shelf shape descriptor. A relational indexing strategy aims to retrieve symbol locations into the target documents by using a combined numerical-relational description of 2D structures. The zones which are likely to contain the queried symbol are validated by a Hough-like voting scheme. In addition, a performance evaluation framework for symbol spotting in graphical documents is proposed. The presented methodology has been evaluated with a benchmarking set of architectural documents achieving good performance results.
%K Document image analysis and recognition
%K Graphics recognition
%K Symbol spotting
%K Vectorial representations
%K Line-drawings
%U http://dx.doi.org/10.1016/j.patrec.2009.10.002
%P 188–201