%0 Journal Article %T Efficient segmentation-free keyword spotting in historical document collections %A Marçal Rusiñol %A David Aldavert %A Ricardo Toledo %A Josep Llados %J Pattern Recognition %D 2015 %V 48 %N 2 %F Marçal Rusiñol2015 %O DAG; ADAS; 600.076; 600.077; 600.061; 601.223; 602.006; 600.055 %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2544), last updated on Wed, 21 Oct 2015 16:02:12 +0200 %X In this paper we present an efficient segmentation-free word spotting method, applied in the context of historical document collections, that follows the query-by-example paradigm. We use a patch-based framework where local patches are described by a bag-of-visual-words model powered by SIFT descriptors. By projecting the patch descriptors to a topic space with the latent semantic analysis technique and compressing the descriptors with the product quantization method, we are able to efficiently index the document information both in terms of memory and time. The proposed method is evaluated using four different collections of historical documents achieving good performances on both handwritten and typewritten scenarios. The yielded performances outperform the recent state-of-the-art keyword spotting approaches. %K Historical documents %K Keyword spotting %K Segmentation-free %K Dense SIFT features %K Latent semantic analysis %K Product quantization %U http://dx.doi.org/10.1016/j.patcog.2014.08.021 %P 545–555