@Article{AlbertGordo2013, author="Albert Gordo and Florent Perronnin and Ernest Valveny", title="Large-scale document image retrieval and classification with runlength histograms and binary embeddings", journal="Pattern Recognition", year="2013", publisher="Elsevier", volume="46", number="7", pages="1898--1905", optkeywords="visual document descriptor", optkeywords="compression", optkeywords="large-scale", optkeywords="retrieval", optkeywords="classification", abstract="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.", optnote="DAG; 600.042; 600.045; 605.203", optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=2306), last updated on Thu, 21 Jan 2016 10:37:56 +0100", issn="0031-3203", doi="10.1016/j.patcog.2012.12.004", opturl="http://dx.doi.org/10.1016/j.patcog.2012.12.004", file=":http://refbase.cvc.uab.es/files/GPV2013.pdf:PDF" }