%0 Journal Article
%T Large-scale document image retrieval and classification with runlength histograms and binary embeddings
%A Albert Gordo
%A Florent Perronnin
%A Ernest Valveny
%J Pattern Recognition
%D 2013
%V 46
%N 7
%I Elsevier
%@ 0031-3203
%F Albert Gordo2013
%O DAG; 600.042; 600.045; 605.203
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2306), last updated on Thu, 21 Jan 2016 10:37:56 +0100
%X We present a new document image descriptor based on multi-scale runlengthhistograms. This descriptor does not rely on layout analysis and can becomputed efficiently. We show how this descriptor can achieve state-of-theartresults on two very different public datasets in classification and retrievaltasks. Moreover, we show how we can compress and binarize these descriptorsto make them suitable for large-scale applications. We can achieve state-ofthe-art results in classification using binary descriptors of as few as 16 to 64bits.
%K visual document descriptor
%K compression
%K large-scale
%K retrieval
%K classification
%U http://dx.doi.org/10.1016/j.patcog.2012.12.004
%U http://refbase.cvc.uab.es/files/GPV2013.pdf
%P 1898-1905