TY - CONF AU - Hongxing Gao AU - Marçal Rusiñol AU - Dimosthenis Karatzas AU - Josep Llados A2 - SPIE-DRR PY - 2014// TI - Fast Structural Matching for Document Image Retrieval through Spatial Databases BT - Document Recognition and Retrieval XXI VL - 9021 KW - Document image retrieval KW - distance transform KW - MSER KW - spatial database N2 - The structure of document images plays a signi cant role in document analysis thus considerable e orts have been made towards extracting and understanding document structure, usually in the form of layout analysis approaches. In this paper, we rst employ Distance Transform based MSER (DTMSER) to eciently extract stable document structural elements in terms of a dendrogram of key-regions. Then a fast structural matching method is proposed to query the structure of document (dendrogram) based on a spatial database which facilitates the formulation of advanced spatial queries. The experiments demonstrate a signi cant improvement in a document retrieval scenario when compared to the use of typical Bag of Words (BoW) and pyramidal BoW descriptors. L1 - http://refbase.cvc.uab.es/files/GRK2014.pdf UR - http://dx.doi.org/10.1117/12.2042458 N1 - DAG; 600.056; 600.061; 600.077 ID - Hongxing Gao2014 ER -