%0 Conference Proceedings %T LSDE: Levenshtein Space Deep Embedding for Query-by-string Word Spotting %A Lluis Gomez %A Marçal Rusiñol %A Dimosthenis Karatzas %B 14th International Conference on Document Analysis and Recognition %D 2017 %F Lluis Gomez2017 %O DAG; 600.084; 600.121 %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2999), last updated on Mon, 07 Dec 2020 14:28:43 +0100 %X n this paper we present the LSDE string representation and its application to handwritten word spotting. LSDE is a novel embedding approach for representing strings that learns a space in which distances between projected points are correlated with the Levenshtein edit distance between the original strings.We show how such a representation produces a more semantically interpretable retrieval from the user’s perspective than other state of the art ones such as PHOC and DCToW. We also conduct a preliminary handwritten word spotting experiment on the George Washington dataset. %U http://refbase.cvc.uab.es/files/GRK2017.pdf %U http://dx.doi.org/10.1109/ICDAR.2017.88