Fast structural matching for document image retrieval through spatial databases

Hongxing Gao; Maçal Rusiñol; Dimosthenis Karatzas; Josep Lladós

doi:10.1117/12.2042458

Translator Disclaimer

24 March 2014 Fast structural matching for document image retrieval through spatial databases

Hongxing Gao, Maçal Rusiñol, Dimosthenis Karatzas, Josep Lladós

Author Affiliations +

Proceedings Volume 9021, Document Recognition and Retrieval XXI; 90210N (2014) https://doi.org/10.1117/12.2042458
Event: IS&T/SPIE Electronic Imaging, 2014, San Francisco, California, United States

Abstract

The structure of document images plays a significant role in document analysis thus considerable efforts have been made towards extracting and understanding document structure, usually in the form of layout analysis approaches. In this paper, we first employ Distance Transform based MSER (DTMSER) to efficiently 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 significant improvement in a document retrieval scenario when compared to the use of typical Bag of Words (BoW) and pyramidal BoW descriptors.

Citation Download Citation

Hongxing Gao, Maçal Rusiñol, Dimosthenis Karatzas, and Josep Lladós "Fast structural matching for document image retrieval through spatial databases", Proc. SPIE 9021, Document Recognition and Retrieval XXI, 90210N (24 March 2014); https://doi.org/10.1117/12.2042458

ACCESS THE FULL ARTICLE