To develop a method for structured document recognition, it is necessary to know the relative position of the graphical elements in a document. In order to deal with this notion, we build a neighbourhood graph based on Vorono¨ı tessellation. We propose to combine the use of this interesting notion of neighbourhood with an existing generic document recognition method, DMOS, which has been used to describe various kinds of documents. This association allows exploiting different aspects of the neighbourhood graph, separating the graph analysis from the knowledge linked to a kind of document, and establishing a bidirectional context-based relation between the analyser and the graph. We apply this method on the analysis of various documents.