In document image analysis the task of segmenting images of ancient printed documents in distinct elements is known to be a very complex problem. In general, these documents are of low quality and can present skew and degradations because of old printing or ink stains. To face these problems we will show and discuss the validity of the Mumford and Shah variational method, based on the ? convergence theory, along with its numerical handling. In particular, we segment and extract the interest regions, constituted by textual and non-textual blocks, from page images of ancient books, combining the variational approach with morphological operations. Study case is the first edition of 'Scienza Nuova' (1725) of Giambattista Vico.

We present a work in progress about extracting words from images of historical printed documents by using fast marching method. Segmentation is a process that allows an image to be divided into disjoint zones, so that extracted areas contain homogeneous characteristics. The numerical method, we used to segment images, is based on the theory of interface evolution, described by the eikonal equation. We adopted the fast marching technique to solve the upwind finite difference approximation of the eikonal equation. Segmentation of ancient documents is generally acknowledged as a very complicated problem because this kind of documents can be low quality, presenting local skew and several degradations due to old printing or ink stains.