LSDE: Levenshtein Space Deep Embedding for Query-by-String Word Spotting

Producció científica: Capítol de llibreCapítolRecercaAvaluat per experts

27 Cites (Scopus)

Resum

In 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.

Idioma originalAnglès
Títol de la publicacióProceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
Pàgines499-504
Nombre de pàgines6
ISBN (electrònic)9781538635865
DOIs
Estat de la publicacióPublicada - 2 de jul. 2017

Sèrie de publicacions

NomProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volum1
ISSN (imprès)1520-5363

Fingerprint

Navegar pels temes de recerca de 'LSDE: Levenshtein Space Deep Embedding for Query-by-String Word Spotting'. Junts formen un fingerprint únic.

Com citar-ho