In this paper, we discuss the elements to be taken into account when choosing one's vectorization method. The paper is extensively based on our own implementations and tests, and concentrates on methods designed to have few, if any, parameters .
We claim that time has come in graphics recognition for choosing stable and robust methods, even—or especially— when this means implementing methods proposed by others, instead of inventing a new algorithm which ends up being a minor variation on an old idea. In this spirit, we present some of the choices our own team has made.
In the context of graphics recognition, arc detection consists in the extraction of circles and arcs from the image of a graphics document or from the segments yielded by its vectorization. Several methods have been proposed for this purpose, and we briefly survey them in this paper. Then, we describe an improved algorithm inspired by two existing methods,… (More)
This paper describes the DocMining platform, that is aimed at providing a general framework for document interpretation. The platform integrates processings that come from different sources and that communicate through the document. A task to be performed is represented by a scenario that describes the processings to be run, and each processing is… (More)