@Article{Mar{\c c}alRusi{\~n}ol2014,
author="Mar{\c{c}}al Rusi{\~n}ol
and Volkmar Frinken
and Dimosthenis Karatzas
and Andrew Bagdanov
and Josep Llados",
title="Multimodal page classification in administrative document image streams",
journal="International Journal on Document Analysis and Recognition",
year="2014",
publisher="Springer Berlin Heidelberg",
volume="17",
number="4",
pages="331--341",
optkeywords="Digital mail room",
optkeywords="Multimodal page classification",
optkeywords="Visual and textual document description",
abstract="In this paper, we present a page classification application in a banking workflow. The proposed architecture represents administrative document images by merging visual and textual descriptions. The visual description is based on a hierarchical representation of the pixel intensity distribution. The textual description uses latent semantic analysis to represent document content as a mixture of topics. Several off-the-shelf classifiers and different strategies for combining visual and textual cues have been evaluated. A final step uses an n-gram model of the page stream allowing a finer-grained classification of pages. The proposed method has been tested in a real large-scale environment and we report results on a dataset of 70,000 pages.",
optnote="DAG; LAMP; 600.056; 600.061; 601.240; 601.223; 600.077; 600.079",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=2523), last updated on Wed, 04 Feb 2015 16:52:34 +0100",
issn="1433-2833",
doi="10.1007/s10032-014-0225-8"
}