%0 Conference Proceedings
%T Browsing Heterogeneous Document Collections by a Segmentation-Free Word  Spotting Method
%A Marçal Rusiñol
%A David Aldavert
%A Ricardo Toledo
%A Josep Llados
%B 11th International Conference on Document Analysis and Recognition
%D 2011
%F Marçal Rusiñol2011
%O DAG;ADAS
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1788), last updated on Tue, 29 Oct 2019 09:43:03 +0100
%X In this paper, we present a segmentation-free word spotting method that is able to deal with heterogeneous document image collections. We propose a patch-based framework where patches are represented by a bag-of-visual-words model powered by SIFT descriptors. A later refinement of the feature vectors is performed by applying the latent semantic indexing technique. The proposed method performs well on both handwritten and typewritten historical document images. We have also tested our method on documents written in non-Latin scripts.
%U https://ieeexplore.ieee.org/document/6065277
%U http://dx.doi.org/10.1109/ICDAR.2011.22
%P 63-67