Spatio-structural Symbol Description with Statistical Feature Add-on

Santosh K.C. (1) , Bart Lamiroy (1) , Laurent Wendling (2)

1 QGAR - Querying Graphics through Analysis and Recognition
2 LIPADE - EA 2517 - Laboratoire d'Informatique Paris Descartes

In this paper, we present a method for symbol description based on both spatio-structural and statistical features computed on elementary visual parts, called 'vocabulary'. This extracted vocabulary is grouped by type (e.g., circle, corner ) and serves as a basis for an attributed relational graph where spatial relational descriptors formalise the links between the vertices, formed by these types, labelled with global shape descriptors. The obtained attributed relational graph description has interesting properties that allows it to be used efficiently for recognising structure and by comparing its attribute signatures. The method is experimentally validated in the context of electrical symbol recognition from wiring diagrams.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Santosh K.C., Bart Lamiroy, Laurent Wendling. Spatio-structural Symbol Description with Statistical Feature Add-on. Young-Bin Kwon, Jean-Marc Ogier. Graphics Recognition. New Trends and Challenges, 7423, Springer-Verlag Berlin Heidelberg, pp.228-237, 2013, Lecture Notes in Computer Science, 978-3-642-36823-3 (Print) 978-3-642-36824-0 (Online). ⟨10.1007/978-3-642-36824-0_22⟩. ⟨hal-00789268⟩