Page Classification for Meta-data Extraction from Digital Collections

Automatic extraction of meta-data from collections of scanned documents (books and journals) is a useful task in order to increase the accessibility of these digital collections. In order to improve the extraction of meta-data, the classification of the page layout into a set of pre-defined classes can be helpful. In this paper we describe a method for classifying document images on the basis of their physical layout, that is described by means of a hierarchical representation: the Modified X-Y tree. The Modified X-Y tree describes a document by means of a recursive segmentation by alternating horizontal and vertical cuts along either spaces or lines. Each internal node of the tree represents a separator (a space or a line), whereas leaves represent regions in the page or separating lines. The Modified X-Y tree is built starting from a symbolic description of the document, instead of dealing directly with the image. The tree is afterwards encoded into a fixed-size representation that takes into account occurrences of tree-patterns in the tree representing the page. Lastly, this feature vector is fed to an artificial neural network that is trained to classify document images. The system is applied to the classification of documents belonging to Digital Libraries, examples of classes taken into account for a journal are “title page”, “index”, “regular page”. Some tests of the system are made on a data-set of more than 600 pages belonging to a journal of the 19th Century.