@InProceedings{AlbertGordo2009, author="Albert Gordo and Ernest Valveny", title="The diagonal split: A pre-segmentation step for page layout analysis \& classification", booktitle="4th Iberian Conference on Pattern Recognition and Image Analysis", year="2009", publisher="Springer Berlin Heidelberg", volume="5524", pages="290--297", abstract="Document classification is an important task in all the processes related to document storage and retrieval. In the case of complex documents, structural features are needed to achieve a correct classification. Unfortunately, physical layout analysis is error prone. In this paper we present a pre-segmentation step based on a divide \& conquer strategy that can be used to improve the page segmentation results, independently of the segmentation algorithm used. This pre-segmentation step is evaluated in classification and retrieval using the selective CRLA algorithm for layout segmentation together with a clustering based on the voronoi area diagram, and tested on two different databases, MARG and Girona Archives.", optnote="DAG", optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=1176), last updated on Tue, 17 Dec 2013 15:58:16 +0100", isbn="978-3-642-02171-8", issn="0302-9743", doi="10.1007/978-3-642-02172-5_38" }